Variable bitrate learned image and video compression with a model using multi-objective optimization

Abstract

Systems, methods, and instrumentalities are disclosed herein for training a video coding model. For example, an apparatus (e.g., for training a video coding model) may obtain a neural network (NN) model. The NN model may be or may include a variable bitrate image and / or a video compression system. In examples, the apparatus may obtain a first parameter that is associated with a first compression bitrate and a second parameter that is associated with a second compression bitrate. The apparatus may select a parameter to train the NN model based on a multi-objective optimization (MOO) based algorithm. The selected parameter may be one of the first parameter or the second parameter. The apparatus may train the NN model based on the selected parameter.

Description

IDVC_2023P00829WO PATENT VARIABLE BITRATE LEARNED IMAGE AND VIDEO COMPRESSION WITH A MODEL USING MULTI- OBJECTIVE OPTIMIZATION CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application No.63 / 544,517, filed October 17, 2023 the contents of which is incorporated by reference herein. BACKGROUND

[0001] Video coding systems may be used to compress digital video signals, e.g., to reduce the storage and / or transmission bandwidth needed for such signals. Video coding systems may include, for example, block-based, wavelet-based, Neural Network (NN)-based, and / or object-based systems. SUMMARY

[0002] Systems, methods, and instrumentalities are disclosed herein for training a video coding model. For example, an apparatus (e.g., an apparatus for training a video coding model) may include a processor. The processor may be configured to perform one or more of the following. In examples, the apparatus may be a video encoding device. In examples, the apparatus may be a video decoding device.

[0003] In examples, the apparatus may obtain a neural network (NN) model. The NN model may be or may include (e.g., may be associated with) a variable bitrate image and / or a video compression system.

[0004] In examples, the apparatus may obtain a parameter (e.g., a first parameter). The apparatus may obtain another parameter (e.g., a second parameter). For example, the apparatus may obtain a first parameter and the second parameter. The first compression bitrate may be, or may include, a range of bitrates. The second parameter may be associated with a second compression bitrate. In examples, the first parameter may be associated with a first compression bitrate. In examples, the second compression bitrate may be, or may include, a target bitrate. In examples, the first parameter may be associated with a set of parameters for a shared parameters that is associated with the range of bitrates. In examples, the second parameter may be associated with a set of parameters that is associated with the target bitrate.

[0005] In examples, the apparatus may select a parameter to train the NN model. For example, the selection of the parameter may be based on a multi-objective optimization (MOO) based algorithm. TheIDVC_2023P00829WO PATENT selected parameter may be one of the first parameter or the second parameter. The selected parameter may be associated with a Pareto optimality. In examples, the apparatus may select the parameter based on the MOO based algorithm by applying a gradient-based algorithm. The gradient-based algorithm may be, may include, and / or may be associated with a multiple gradient descent algorithm.

[0006] In examples, the apparatus may obtain one or more (e.g., multiple) loss functions. For example, a (e.g., each) loss function may be associated with compression that is targeted at different bitrates. In examples, the apparatus may obtain a first loss function and a second loss function. The first loss function may be associated with a first compression bitrate. The second loss function may be associated with a second compression bitrate. The first compression bitrate may differ from the second compression bitrate.

[0007] In examples, a (e.g., each) loss function described herein may be associated with one or more (e.g., all) parameters of the NN based system and / or one or more other parameters of the system.

[0008] In examples, a (e.g., each) loss function may be configured to an objective for a training and / or optimization algorithm, e.g., to minimize or maximize the objective simultaneously. For example, the apparatus may configure a multi-objective optimization (MOO) algorithm. The apparatus may use an MOO algorithm minimize or maximize one or more (e.g., all) objectives, e.g., simultaneously.

[0009] In examples, the apparatus may train the NN model and / or one or more other parameters of the system. For example, the apparatus may train the NN model by applying a gradient-based MOO algorithm to the NN and / or to one or more parameters (e.g., system parameters), e.g., to minimize or maximize one or more (e.g., all) objectives simultaneously. The NN model and / or the system parameters may be updated and / or learned, e.g., during the training using gradients associated with one or more (e.g., all) the objectives. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG.1A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented.

[0011] FIG.1B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG.1A according to an embodiment.

[0012] FIG.1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG.1A according to an embodiment.IDVC_2023P00829WO PATENT

[0013] FIG.1D is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG.1A according to an embodiment.

[0014] FIG.2 illustrates an example video encoder.

[0015] FIG.3 illustrates an example video decoder.

[0016] FIG.4 illustrates an example of a system in which various aspects and examples may be implemented.

[0017] FIG.5 illustrates an example autoencoder-based compression architecture.

[0018] FIG.6 illustrates an example training of a fully factorized prior model.

[0019] FIG.7 illustrates an example auto-encoder with a hyperprior approach.

[0020] FIG.8 illustrates example comparisons between an end-to-end image compression procedure described herein and a variable bitrate compression framework, e.g., based on varying the ^ parameter. DETAILED DESCRIPTION

[0021] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings.

[0022] FIG.1A is a diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single-carrier FDMA (SC-FDMA), zero-tail unique-word DFT-Spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0023] As shown in FIG.1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a RAN 104 / 113, a CN 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in aIDVC_2023P00829WO PATENT wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a “station” and / or a “STA”, may be configured to transmit and / or receive wireless signals and may include a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (IoT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a UE.

[0024] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or the other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node-B, an eNode B, a Home Node B, a Home eNode B, a gNB, a NR NodeB, a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0025] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.IDVC_2023P00829WO PATENT

[0026] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0027] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC- FDMA, and the like. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink (DL) Packet Access (HSDPA) and / or High-Speed UL Packet Access (HSUPA).

[0028] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0029] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access, which may establish the air interface 116 using New Radio (NR).

[0030] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., an eNB and a gNB).

[0031] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA20001X, CDMA2000 EV-DO, Interim Standard 2000 (IS- 2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0032] The base station 114b in FIG.1A may be a wireless router, Home Node B, Home eNode B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., forIDVC_2023P00829WO PATENT use by drones), a roadway, and the like. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR etc.) to establish a picocell or femtocell. As shown in FIG.1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0033] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 / 115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG.1A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing a NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0034] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or the other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 / 113 or a different RAT.

[0035] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102cIDVC_2023P00829WO PATENT shown in FIG.1A may be configured to communicate with the base station 114a, which may employ a cellular- based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0036] FIG.1B is a system diagram illustrating an example WTRU 102. As shown in FIG.1B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0037] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. As suggested above, the processor 118 may include a plurality of processors. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG.1B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0038] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0039] Although the transmit / receive element 122 is depicted in FIG.1B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0040] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive elementIDVC_2023P00829WO PATENT 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11, for example.

[0041] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0042] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li- ion), etc.), solar cells, fuel cells, and the like.

[0043] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0044] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radioIDVC_2023P00829WO PATENT unit, a digital music player, a media player, a video game player module, an Internet browser, a Virtual Reality and / or Augmented Reality (VR / AR) device, an activity tracker, and the like. The peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0045] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the UL (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WRTU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the UL (e.g., for transmission) or the downlink (e.g., for reception)).

[0046] FIG.1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0047] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a.

[0048] Each of the eNode-Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, and the like. As shown in FIG.1C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0049] The CN 106 shown in FIG.1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. While each of the foregoing elements are depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.IDVC_2023P00829WO PATENT

[0050] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, 160c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0051] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via the S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter-eNode B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0052] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0053] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0054] Although the WTRU is described in FIGS.1A-1D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0055] In representative embodiments, the other network 112 may be a WLAN.

[0056] A WLAN in Infrastructure Basic Service Set (BSS) mode may have an Access Point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a Distribution System (DS) or another type of wired / wireless network that carries traffic in to and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example,IDVC_2023P00829WO PATENT where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. The peer-to- peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802.11e DLS or an 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an “ad-hoc” mode of communication.

[0057] When using the 802.11ac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signaling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented, for example in in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0058] High Throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadjacent 20 MHz channel to form a 40 MHz wide channel.

[0059] Very High Throughput (VHT) STAs may support 20MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two non- contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above described operation for the 80+80 configuration may be reversed, and the combined data may be sent to the Medium Access Control (MAC).

[0060] Sub 1 GHz modes of operation are supported by 802.11af and 802.11ah. The channel operating bandwidths, and carriers, are reduced in 802.11af and 802.11ah relative to those used in 802.11n, andIDVC_2023P00829WO PATENT 802.11ac.802.11af supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support Meter Type Control / Machine- Type Communications, such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., only support for) certain and / or limited bandwidths. The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0061] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.11ah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0062] In the United States, the available frequency bands, which may be used by 802.11ah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.11ah is 6 MHz to 26 MHz depending on the country code.

[0063] FIG.1D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0064] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 108b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a,IDVC_2023P00829WO PATENT 180b, 180c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0065] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., containing varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0066] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non- standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0067] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards User Plane Function (UPF) 184a, 184b, routing of control plane information towardsIDVC_2023P00829WO PATENT Access and Mobility Management Function (AMF) 182a, 182b and the like. As shown in FIG.1D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0068] The CN 115 shown in FIG.1D may include at least one AMF 182a, 182b, at least one UPF 184a,184b, at least one Session Management Function (SMF) 183a, 183b, and possibly a Data Network (DN) 185a, 185b. While each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0069] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different PDU sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of NAS signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b in order to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for machine type communication (MTC) access, and / or the like. The AMF 162 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0070] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating UE IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP-based, non-IP based, Ethernet-based, and the like.

[0071] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP- enabled devices. The UPF 184a, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.IDVC_2023P00829WO PATENT

[0072] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to a local Data Network (DN) 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0073] In view of Figures 1A-1D, and the corresponding description of Figures 1A-1D, one or more, or all, of the functions described herein with regard to one or more of: WTRU 102a-d, Base Station 114a-b, eNode-B 160a-c, MME 162, SGW 164, PGW 166, gNB 180a-c, AMF 182a-b, UPF 184a-b, SMF 183a-b, DN 185a-b, and / or any other device(s) described herein, may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0074] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or may perform testing using over-the-air wireless communications.

[0075] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a non-deployed (e.g., testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be testing equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0076] This application describes a variety of aspects, including tools, features, examples, models, approaches, etc. Many of these aspects are described with specificity and, at least to show the individualIDVC_2023P00829WO PATENT characteristics, are often described in a manner that may sound limiting. However, this is for purposes of clarity in description, and does not limit the application or scope of those aspects. Indeed, all of the different aspects may be combined and interchanged to provide further aspects. Moreover, the aspects may be combined and interchanged with aspects described in earlier filings as well.

[0077] The aspects described and contemplated in this application may be implemented in many different forms. FIGs.5-8 described herein may provide some examples, but other examples are contemplated. The discussion of FIGs.5-8 does not limit the breadth of the implementations. At least one of the aspects generally relates to video encoding and decoding, and at least one other aspect generally relates to transmitting a bitstream generated or encoded. These and other aspects may be implemented as a method, an apparatus, a computer readable storage medium having stored thereon instructions for encoding or decoding video data according to any of the methods described, and / or a computer readable storage medium having stored thereon a bitstream generated according to any of the methods described.

[0078] In the present application, the terms “reconstructed” and “decoded” may be used interchangeably, the terms “pixel” and “sample” may be used interchangeably, and the terms “image,” “picture” and “frame” may be used interchangeably.

[0079] Various methods are described herein, and each of the methods comprises one or more steps or actions for achieving the described method. Unless a specific order of steps or actions is required for the proper operation of the method, the order and / or use of specific steps and / or actions may be modified or combined. Additionally, terms such as “first,” “second,” etc. may be used in various examples to modify an element, component, step, operation, etc., such as, for example, a “first decoding” and a “second decoding.” Use of such terms does not imply an ordering to the modified operations unless specifically required. So, in this example, the first decoding need not be performed before the second decoding, and may occur, for example, before, during, or in an overlapping time period with the second decoding.

[0080] As described herein, a video coding and / or transform coding part, such as multiple transform selection (MTS) tools may be configured. In a coding tool, one or more transforms, e.g., discrete cosine transform (DCT)5, discrete sine transform (DST)4, DST1, and / or identity transform (IDT) may be added to MTS (e.g., in addition to DCT8 and / or DST7 in a coding tool). The one or more transforms may provide rate- distortion gain. The one or more transforms may increase complexity to a device, such as an encoder, e.g., as one or more additional check operations are performed during the rate-distortion optimization loop. As described herein, an implicit MTS may be used to infer transform (e.g., the best transform) regarding current block information.IDVC_2023P00829WO PATENT

[0081] Various methods and other aspects described in this application may be used to modify modules, for example, decoding modules, of a video encoder (200) and a video decoder (300) as shown in FIG.2 and FIG. 3. Moreover, the subject matter disclosed herein may be applied, for example, to any type, format or version of video coding, whether described in a standard or a recommendation, whether pre-existing or future-developed, and extensions of any such standards and recommendations. Unless indicated otherwise, or technically precluded, the aspects described in this application may be used individually or in combination.

[0082] Various numeric values are used in examples described in the present application, such as bits, bit depth, etc. These and other specific values are for purposes of describing examples and the aspects described are not limited to these specific values.

[0083] FIG.2 illustrates a diagram showing an example video encoder. Variations of example encoder 200 are contemplated, but the encoder 200 is described below for purposes of clarity without describing all expected variations.

[0084] Before being encoded, the video sequence may go through pre-encoding processing (201), for example, applying a color transform to the input color picture (e.g., conversion from RGB 4:4:4 to YCbCr 4:2:0), or performing a remapping of the input picture components in order to get a signal distribution more resilient to compression (for instance using a histogram equalization of one of the color components). Metadata may be associated with the pre-processing and attached to the bitstream.

[0085] In the encoder (200), a picture may be encoded by one or more encoder elements as described herein. The picture to be encoded may be partitioned (202) and processed in units of, for example, coding units (CUs). A unit may be encoded using, for example, an intra mode or an inter mode. If a unit is encoded in an intra mode, the encoder may perform intra prediction (260). If a unit is encoded in an inter mode, the encoder may perform motion estimation (275) and / or motion compensation (270). The encoder may decide (205) which one of the intra mode or inter mode to use for encoding the unit and may indicate the intra / inter decision by, for example, a prediction mode indication, such as a prediction mode flag. Prediction residuals may be calculated, for example, by subtracting (210) the predicted block from the image block, e.g., the original image block.

[0086] The prediction residuals may be transformed (225) and quantized (230). The quantized transform coefficients, as well as one or more motion vectors and / or other syntax elements, may be entropy coded (245) to output a bitstream. The encoder may skip the transform and apply quantization directly to the non- transformed residual signal. The encoder may bypass transform and / or quantization. For example, the residual may be coded directly without the application of the transform and / or the quantization processes.IDVC_2023P00829WO PATENT

[0087] The encoder may decode an encoded block to provide a reference for further predictions. The quantized transform coefficients may be de-quantized (240), and inverse transformed (250) to decode prediction residuals. Combining (255) the decoded prediction residuals and the predicted block, an image block may be reconstructed. In-loop filters (265) may be applied to the reconstructed picture to perform, for example, deblocking / sample adaptive offset (SAO) filtering to reduce encoding artifacts. The filtered image may be stored at a reference picture buffer (280).

[0088] FIG.3 illustrates a diagram showing an example of a video decoder. In example decoder (300), a bitstream may be decoded by one or more decoder elements as described herein. The video decoder (300) may perform a decoding pass reciprocal to the encoding pass as described in FIG.2. The encoder (200) may perform video decoding as part of encoding video data.

[0089] In examples, the input of the decoder may be, or may include, a video bitstream, which may be generated by a video encoder (200). The bitstream may be entropy decoded (330) to obtain transform coefficients, motion vectors, and / or other coded information. The picture partition information may indicate how the picture is partitioned. The decoder may divide (335) the picture according to the decoded picture partitioning information. The transform coefficients may be de-quantized (340), and inverse transformed (350) to decode the prediction residuals. Combining (355) the decoded prediction residuals and the predicted block, an image block may be reconstructed. The predicted block may be obtained (370) from intra prediction (360) or motion-compensated prediction (e.g., inter prediction) (375). In-loop filters (365) may be applied to the reconstructed image. The filtered image may be stored at a reference picture buffer (380). In examples, for a given picture, the contents of the reference picture buffer (380) on the decoder (300) side may be similar (e.g., identical) to the contents of the reference picture buffer (280) on the encoder (200) side for the same picture.

[0090] The decoded picture may go through post-decoding processing (385), for example, an inverse color transform (e.g., conversion from YCbCr 4:2:0 to RGB 4:4:4) and / or an inverse remapping performing the inverse of the remapping process performed in the pre-encoding processing (201). The post-decoding processing may use metadata derived in the pre-encoding processing and signaled in the bitstream. In an example, the decoded images (e.g., after application of the in-loop filters (365) and / or after post-decoding processing (385), if post-decoding processing is used) may be sent to a display device for rendering to a user.

[0091] FIG.4 illustrates a diagram showing an example of a system in which various aspects and examples described herein may be implemented. A system (400) may be embodied as a device including the various components described below and may be configured to perform one or more of the aspects described in this document. Examples of such devices may include, but are not limited to, various electronic devices such asIDVC_2023P00829WO PATENT personal computers, laptop computers, smartphones, tablet computers, digital multimedia set top boxes, digital television receivers, personal video recording systems, connected home appliances, and servers. One or more elements of the system (400), singly or in combination, may be embodied in a single integrated circuit (IC), multiple ICs, and / or discrete components. For example, in at least one example, the processing and encoder / decoder elements of the system (400) may be distributed across multiple ICs and / or discrete components. In various examples, the system (400) may be communicatively coupled to one or more other systems, or other electronic devices, via, for example, a communications bus or through dedicated input and / or output ports. In various examples, the system (400) may be configured to implement one or more of the aspects described in this document.

[0092] The system (400) may include at least one processor (410) configured to execute instructions loaded therein for implementing, for example, the various aspects described herein. The processor (410) may include embedded memory, input output interface, and / or various other circuitries as known in the art. The system (400) may include at least one memory (420) (e.g., a volatile memory device, and / or a non-volatile memory device). The system (400) may include a storage device (440), which may include non-volatile memory and / or volatile memory, including, but not limited to, Electrically Erasable Programmable Read-Only Memory (EEPROM), Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), flash, magnetic disk drive, and / or optical disk drive. The storage device (440) may include an internal storage device, an attached storage device (including detachable and non-detachable storage devices), and / or a network accessible storage device, as non-limiting examples.

[0093] The system (400) may include an encoder / decoder module (430) configured, for example, to process data to provide an encoded video or decoded video, and the encoder / decoder module (430) may include its own processor and memory. The encoder / decoder module (430) may represent a module(s) that may be included in a device to perform the encoding and / or decoding functions. As is known, a device may include one or both of the encoding and decoding modules. Additionally, the encoder / decoder module (430) may be implemented as a separate element of system (400) or may be incorporated within the processor (410) as a combination of hardware and software as known to those skilled in the art.

[0094] Program code to be loaded onto the processor (410) or the encoder / decoder (430) to perform the various aspects described herein may be stored in the storage device (440) and subsequently loaded onto the memory (420) for execution by the processor (410). In accordance with various examples, one or more of the processor (410), the memory (420), the storage device (440), and the encoder / decoder module (430) mayIDVC_2023P00829WO PATENT store one or more of various items during the performance of the processes described herein. Such stored items may include, but are not limited to, the input video, the decoded video or portions of the decoded video, the bitstream, matrices, variables, and intermediate or final results from the processing of equations, formulas, operations, and operational logic.

[0095] In some examples, a memory inside of the processor (410) and / or the encoder / decoder module (430) may be used to store instructions and to provide working memory for processing that is needed during encoding or decoding. In other examples, however, a memory external to the processing device (for example, the processing device may be either the processor (410) or the encoder / decoder module (430)) may be used for one or more of these functions. The external memory may be the memory (420) and / or the storage device (440), for example, a dynamic volatile memory and / or a non-volatile flash memory. In several examples, an external non-volatile flash memory is used to store the operating system of, for example, a television. In at least one example, a fast external dynamic volatile memory such as a RAM is used as working memory for video encoding and decoding operations.

[0096] The input to the elements of the system (400) may be provided through various input devices as indicated in the block (445). Such input devices may include, but are not limited to, (i) a radio frequency (RF) portion that receives an RF signal transmitted, for example, over the air by a broadcaster, (ii) a Component (COMP) input terminal (or a set of COMP input terminals), (iii) a Universal Serial Bus (USB) input terminal, and / or (iv) a High Definition Multimedia Interface (HDMI) input terminal. Other examples, not shown in FIG.4, may include composite video.

[0097] In various examples, the input devices of the block (445) may have associated respective input processing elements as known in the art. For example, the RF portion may be associated with elements suitable for (i) selecting a desired frequency (also referred to as selecting a signal, or band-limiting a signal to a band of frequencies), (ii) downconverting the selected signal, (iii) band-limiting again to a narrower band of frequencies to select (for example) a signal frequency band which may be referred to as a channel in certain examples, (iv) demodulating the downconverted and band-limited signal, (v) performing error correction, and / or (vi) demultiplexing to select the desired stream of data packets. The RF portion of various examples may include one or more elements to perform these functions, for example, frequency selectors, signal selectors, band-limiters, channel selectors, filters, downconverters, demodulators, error correctors, and demultiplexers. The RF portion may include a tuner that performs various of these functions, including, for example, downconverting the received signal to a lower frequency (for example, an intermediate frequency or a near- baseband frequency) or to baseband. In one set-top box example, the RF portion and its associated inputIDVC_2023P00829WO PATENT processing element may receive an RF signal transmitted over a wired (for example, cable) medium, and may perform frequency selection by filtering, downconverting, and filtering again to a desired frequency band. Various examples rearrange the order of the above-described (and other) elements, may remove some of these elements, and / or add other elements performing similar or different functions. Adding elements may include inserting elements in between existing elements, such as, for example, inserting amplifiers and an analog-to-digital converter. In various examples, the RF portion may include an antenna.

[0098] The USB and / or HDMI terminals may include respective interface processors for connecting system (400) to other electronic devices across USB and / or HDMI connections. It is to be understood that various aspects of input processing, for example, Reed-Solomon error correction, may be implemented, for example, within a separate input processing IC or within the processor (410) as necessary. Similarly, aspects of USB or HDMI interface processing may be implemented within separate interface ICs or within the processor (410) as necessary. The demodulated, error corrected, and demultiplexed stream may be provided to various processing elements, including, for example, the processor (410) and the encoder / decoder (430) operating in combination with the memory and the storage elements to process the datastream as necessary for presentation on an output device.

[0099] Various elements of system (400) may be provided within an integrated housing. Within the integrated housing, the various elements may be interconnected and transmit data therebetween using the suitable connection arrangement (425), for example, an internal bus as known in the art, including the Inter-IC (I2C) bus, wiring, and printed circuit boards.

[0100] The system (400) may include a communication interface (450) that enables communication with other devices via a communication channel (460). The communication interface (450) may include, but is not limited to, a transceiver configured to transmit and to receive data over the communication channel (460). The communication interface (450) may include, but is not limited to, a modem or network card and the communication channel (460) may be implemented, for example, within a wired and / or a wireless medium.

[0101] Data may be streamed, or otherwise provided, to the system (400), in various examples, using a wireless network such as a Wi-Fi network, for example IEEE 802.11 (IEEE refers to the Institute of Electrical and Electronics Engineers). The Wi-Fi signal of these examples is received over the communications channel (460) and the communications interface (450) which are adapted for Wi-Fi communications. The communications channel (460) of these examples may be typically connected to an access point or router that provides access to external networks including the Internet for allowing streaming applications and other over- the-top communications. Other examples may provide streamed data to the system (400) using a set-top boxIDVC_2023P00829WO PATENT that delivers the data over the HDMI connection of the input block (445). Still other examples provide streamed data to the system (400) using the RF connection of the input block (445). As indicated above, various examples may provide data in a non-streaming manner. Additionally, various examples use wireless networks other than Wi-Fi, for example a cellular network or a Bluetooth® network.

[0102] The system (400) may provide an output signal to various output devices, including a display (475), speakers (485), and / or other peripheral devices (495). The display (475) of various examples may include one or more of, for example, a touchscreen display, an organic light-emitting diode (OLED) display, a curved display, and / or a foldable display. The display (475) may be for a television, a tablet, a laptop, a cell phone (mobile phone), or other device. The display (475) may also be integrated with other components (for example, as in a smart phone), or separate (for example, an external monitor for a laptop). The other peripheral devices (495) may include, in various examples, one or more of a stand-alone digital video disc (or digital versatile disc) (DVD, for both terms), a disk player, a stereo system, and / or a lighting system. Various examples may use one or more peripheral devices (495) that provide a function based on the output of the system (400). For example, a disk player performs the function of playing the output of the system (400).

[0103] In various examples, control signals are communicated between the system (400) and the display (475), the speakers (485), or other peripheral devices (495) using signaling such as AV.Link, Consumer Electronics Control (CEC), or other communications may protocol that enable device-to-device control with or without user intervention. The output devices may be communicatively coupled to system (400) via dedicated connections through respective interfaces (470, 480, and 490). Alternatively, the output devices may be connected to the system (400) using the communications channel (460) via the communications interface (450). The display (475) and speakers (485) may be integrated into a single unit with the other components of the system (400) in an electronic device such as, for example, a television. In various examples, the display interface (470) may include a display driver, such as, for example, a timing controller (T Con) chip.

[0104] The display (475) and the speakers (485) may alternatively be separated from one or more of the other components, for example, if the RF portion of input (445) is part of a separate set-top box. In various examples in which the display (475) and the speakers (485) may be external components, the output signal may be provided via dedicated output connections, including, for example, HDMI ports, USB ports, or COMP outputs.

[0105] The examples may be carried out by computer software implemented by the processor (410) or by hardware, or by a combination of hardware and software. As a non-limiting example, the examples may be implemented by one or more integrated circuits. The memory (420) may be of any type appropriate to theIDVC_2023P00829WO PATENT technical environment and may be implemented using any appropriate data storage technology, such as optical memory devices, magnetic memory devices, semiconductor-based memory devices, fixed memory, and removable memory, as non-limiting examples. The processor (410) may be of any type appropriate to the technical environment, and may encompass one or more microprocessors, general purpose computers, special purpose computers, and processors based on a multi-core architecture, as non-limiting examples.

[0106] Various implementations involve decoding. “Decoding,” as used in this application, can encompass all or part of the processes performed, for example, on a received encoded sequence in order to produce a final output suitable for display. In various examples, such processes include one or more of the processes typically performed by a decoder, for example, entropy decoding, inverse quantization, inverse transformation, and differential decoding. In various examples, such processes also, or alternatively, may include processes performed by a decoder of various implementations described in this application.

[0107] As further examples, in one example “decoding” refers only to entropy decoding, in another example “decoding” refers only to differential decoding, and in another example “decoding” refers to a combination of entropy decoding and differential decoding. Whether the phrase “decoding process” is intended to refer specifically to a subset of operations or generally to the broader decoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

[0108] Various implementations involve encoding. In an analogous way to the above discussion about “decoding,” “encoding” as used in this application can encompass all or part of the processes performed, for example, on an input video sequence in order to produce an encoded bitstream. In various examples, such processes include one or more of the processes typically performed by an encoder, for example, partitioning, differential encoding, transformation, quantization, and entropy encoding. In various examples, such processes also, or alternatively, may include processes performed by an encoder of various implementations described in this application.

[0109] As further examples, in one example “encoding” refers only to entropy encoding, in another example “encoding” refers only to differential encoding, and in another example “encoding” refers to a combination of differential encoding and entropy encoding. Whether the phrase “encoding process” is intended to refer specifically to a subset of operations or generally to the broader encoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

[0110] When a figure is presented as a flow diagram, it should be understood that it also provides a block diagram of a corresponding apparatus. Similarly, when a figure is presented as a block diagram, it should be understood that it also provides a flow diagram of a corresponding method / process.IDVC_2023P00829WO PATENT

[0111] The implementations and aspects described herein may be implemented in, for example, a method or a process, an apparatus, a software program, a data stream, or a signal. Even if only discussed in the context of a single form of implementation (for example, discussed only as a method), the implementation of features discussed can also be implemented in other forms (for example, an apparatus or program). An apparatus may be implemented in, for example, appropriate hardware, software, and firmware. The methods may be implemented in, for example, a processor, which refers to processing devices in general, including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. Processors also include communication devices, such as, for example, computers, cell phones, portable / personal digital assistants (PDAs), and other devices that facilitate communication of information between end-users.

[0112] Reference to “one example” or “an example” or “one implementation” or “an implementation,” as well as other variations thereof, means that a particular feature, structure, characteristic, and so forth described in connection with the example is included in at least one example. Thus, the appearances of the phrase “in one example” or “in an example” or “in one implementation” or “in an implementation,” as well any other variations, appearing in various places throughout this application are not necessarily all referring to the same example.

[0113] Additionally, this application may refer to “determining” various pieces of information. Determining the information can include one or more of, for example, estimating the information, calculating the information, predicting the information, or retrieving the information from memory. Obtaining may include receiving, retrieving, constructing, generating, and / or determining.

[0114] Further, this application may refer to “accessing” various pieces of information. Accessing the information can include one or more of, for example, receiving the information, retrieving the information (for example, from memory), storing the information, moving the information, copying the information, calculating the information, determining the information, predicting the information, or estimating the information.

[0115] Additionally, this application may refer to “receiving” various pieces of information. Receiving is, as with “accessing,” intended to be a broad term. Receiving the information can include one or more of, for example, accessing the information, or retrieving the information (for example, from memory). Further, “receiving” is typically involved, in one way or another, during operations such as, for example, storing the information, processing the information, transmitting the information, moving the information, copying the information, erasing the information, calculating the information, determining the information, predicting the information, or estimating the information.

[0116] It is to be appreciated that the use of any of the following “ / ”, “and / or”, and “at least one of”, for example, in the cases of “A / B”, “A and / or B” and “at least one of A and B”, is intended to encompass theIDVC_2023P00829WO PATENT selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of both options (A and B). As a further example, in the cases of “A, B, and / or C” and “at least one of A, B, and C”, such phrasing is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of the third listed option (C) only, or the selection of the first and the second listed options (A and B) only, or the selection of the first and third listed options (A and C) only, or the selection of the second and third listed options (B and C) only, or the selection of all three options (A and B and C). This may be extended, as is clear to one of ordinary skill in this and related arts, for as many items as are listed.

[0117] Also, as used herein, the word “signal” refers to, among other things, indicating something to a corresponding decoder. Encoder signals may include, for example, an encoding function on an input for a block using a precision factor, etc. In this way, in an example, the same parameter is used at both the encoder side and the decoder side. Thus, for example, an encoder can transmit (explicit signaling) a particular parameter to the decoder so that the decoder can use the same particular parameter. Conversely, if the decoder already has the particular parameter as well as others, then signaling may be used without transmitting (implicit signaling) to simply allow the decoder to know and select the particular parameter. By avoiding transmission of any actual functions, a bit savings may be realized in various examples. It is to be appreciated that signaling may be accomplished in a variety of ways. For example, one or more syntax elements, flags, and so forth are used to signal information to a corresponding decoder in various examples. While the preceding relates to the verb form of the word “signal,” the word “signal” may (e.g., may also) be used herein as a noun.

[0118] As will be evident to one of ordinary skill in the art, implementations may produce a variety of signals formatted to carry information that may be, for example, stored or transmitted. The information can include, for example, instructions for performing a method, or data produced by one of the described implementations. For example, a signal may be formatted to carry the bitstream of a described example. Such a signal may be formatted, for example, as an electromagnetic wave (for example, using a radio frequency portion of the spectrum) or as a baseband signal. The formatting may include, for example, encoding a data stream and modulating a carrier with the encoded data stream. The information that the signal carries may be, for example, analog or digital information. The signal may be transmitted over a variety of different wired or wireless links, as is known. The signal may be stored on, or accessed, or received from a processor-readable medium.

[0119] Many examples are described herein. Features of examples may be provided alone or in any combination, across various claim categories and types. Further, examples may include one or more of theIDVC_2023P00829WO PATENT features, devices, or aspects described herein, alone or in any combination, across various claim categories and types. For example, features described herein may be implemented in a bitstream or signal that includes information generated as described herein. The information may allow a decoder to decode a bitstream, the encoder, bitstream, and / or decoder according to any of the embodiments described. For example, features described herein may be implemented by creating and / or transmitting and / or receiving and / or decoding a bitstream or signal. For example, features described herein may be implemented a method, process, apparatus, medium storing instructions, medium storing data, or signal. For example, features described herein may be implemented by a TV, set-top box, cell phone, tablet, or other electronic device that performs decoding. The TV, set-top box, cell phone, tablet, or other electronic device may display (e.g., using a monitor, screen, or other type of display) a resulting image (e.g., an image from residual reconstruction of the video bitstream). The TV, set-top box, cell phone, tablet, or other electronic device may receive a signal including an encoded image and perform decoding.

[0120] These examples may be performed by a device with at least one processor. The device may be an encoder or a decoder. These examples may be performed by a computer program product which is stored on a non-transitory computer readable medium and includes program code instructions. These examples may be performed by a computer program comprising program code instructions.

[0121] A neural network (NN) algorithm may be configured (e.g., applied) to an image and / or video compression. A NN, such as a deep NN, may be applied to compression. For example, a NN may be configured to replace one or more modules associated with a video standard and / or replace the whole structure by one or more end-to-end learned NN-based procedures.

[0122] In examples, one or more of the following approaches may be configured: one or more encoder methods, methods that are built with (e.g., on top of) one or more standards, and / or one or more end-to-end NN-based codecs.

[0123] One or more encoder methods may use one or more NN-based algorithms to enhance or speed-up an encoder of a codec.

[0124] One or more methods that are built with (e.g., on top of) one or more standards, one or more modules of codecs may be replaced by one or more NN-based methods, e.g., post-filters, prediction modules, etc.

[0125] One or more end-to-end NN-based codecs and / or coding tools, one or more compression schemes, such as prediction, transform, quantization, and / or entropy coding, may be disrupted.IDVC_2023P00829WO PATENT

[0126] One or more end-to-end NN-based codecs and / or coding tools may be described herein.

[0127] One or more coding methods may apply prediction modes, e.g., pre-defined prediction modes, and / or transforms. One or more NN-based methods may use (e.g., rely on) one or more parameters that are learned on a data set (e.g., a large data set) during a training stage. For example, one or more NN-based methods may rely on one or more parameters that are learned on a large data set during a training stage by iteratively minimizing a loss function. In the case of the image and / or video compression, the loss function may be defined by a rate-distortion cost. The rate may stand for an estimated bitrate of an encoded bitstream (e.g., video data). The distortion may quantify a quality of a decoded video, e.g., against an input (e.g., an original input). The quality of the decoded input image may be optimized, for example, based on a measure of the mean squared error and / or an approximation of a human-perceived visual quality.

[0128] FIG.5 illustrates an example auto-encoder architecture. For example, FIG.5 may illustrate an example fully factorized-prior-based auto-encoder for image compression. As illustrated in FIG.5, an exemplary end-to-end compression system may be provided. The input ^ to the encoder part of the network may include one or more of the following: an image or frame of a video; a part of an image; a tensor representing a group of images; or a tensor representing a part (e.g., crop) of a group of images.

[0129] In examples, the input may have one or more components, e.g., monochrome, RGB or YCbCr components.

[0130] The input ^ may be fed into an encoder network ^^, known as analysis transform. ^^may be asequence of convolutional layers with activation functions. The convolutions may be or may include a mechanism to spatially down-sample the input. For example, the convolutions may select a convolution with stride of 2 in vertical and / or horizontal directions. The convolution may result in an output having a half the size of the input in one or more (e.g., both) dimensions. The output of a convolution may be a tensor of shape C×H×W. H and W may be the spatial height and width, respectively. C may correspond to an adjustable number of channels. For an RGB image, the first convolution of ^^may take as input a tensor of 3 channels which correspond to the color components. The encoder network may be seen as a learned transform. For example, the learned transform may be lossy as there are generally fewer elements in the output latent tensor than the source C×H×W input. The output of the analysis, e.g., mostly in the form of a 3-way array, referred to as a 3-D tensor may be called as a latent representation or a tensor of latent variables. From a broader perspective, a set of latent variables may construct a latent space, which may be frequently used in the context of neural network-based end-to-end compression.IDVC_2023P00829WO PATENT

[0131] The output ^ ൌ ^^^^^ may be quantized. For example, the quantized output may result in a tensor ^^. The tensor ^^ may be entropy coded into a binary stream (e.g., bitstream or video data) for storage and / or transmission.

[0132] At a decoder, the bitstream and / or the video data may be entropy decoded (ED) to obtain ^^.

[0133] A decoder network, such as ^^, may be called a synthesis transform. For example, a decoder network may generate a reconstructed input: ^^ ൌ ^^^^^^. The reconstructed input may be an approximation ofan input ^ (e.g., the original ^) from the quantized latent representation ^^. ^^may be a sequence of up-sampling convolutions, e.g., transpose convolutions or convolutions followed by up-sampling filters. The decoder network may be seen as a learned inverse transform and / or a denoising and generative transform.

[0134] A compression system, such as an image and / or a video compression system, may have one or more factorized prior and / or hyper prior based compression architectures.

[0135] In examples, the performance of a compression system may be measured as a tradeoff between a number of bits needed to transmit versus a quality of a decoded content. A compression model may be trained using a loss form, such as following the Lagrangian form: ^ ൌ ^ ^ ^^. R may represent the rate and / or bitrate. D may represent the distortion of the decoded content.

[0136] As described herein, FIG.5 illustrates an example autoencoder-based compression architecture. The example autoencoder-based compression architecture illustrated in FIG.5 may include an inference configuration (e.g., an actual inference configuration) that includes an encoder producing a bitstream (e.g., video data). The produced bitstream (e.g., the video data) may be transmitted and / or decoded by a decoder. To have a bitstream (e.g., video data) with a bit rate R (e.g., a small bitrate R), the probability of the quantized latent tensor ^^ may be known (e.g., may need to be known) by a lossless compression algorithm, such as an arithmetic coding, used at the encoder and / or the decoder.

[0137] FIG.6 illustrates an example training of a fully factorized prior model. As illustrated in FIG.6, entropy encoding / decoding may be non-differentiable. The rate term R may be represented with an entropy of ^^. The entropy of ^^ may be estimated via a differentiable proxy, e.g., using a learnedof ^^, as illustrated in FIG.6. In the so-called fully factorized prior (e.g., probability) model of ^^, a latent variable within a channel may be assumed to be independent and / or identically distributed (i.i.d.). For example, the joint probability distribution of variables within a channel of the latent tensor ^^ may be factorized (e.g., thus the name of the model) over an identical probability distribution of a variable (e.g., each variable).IDVC_2023P00829WO PATENT

[0138] As for the distortion, such NNs may be trained using one or more of the following types of losses: a loss based on an objective metric and / or a loss based on a subjective metric.

[0139] In examples, a loss based on an objective metric may be Mean Squared Error (MSE), e.g., illustrated ^^^ െ ^^ଶଶ in FIG.6. In examples, loss based on an objective metric may be based on structural similarity (SSIM). The results may not be perceptually as good as the second type, but the fidelity to the signal, such as the original signal, (e.g., the image) may be higher.

[0140] In examples, a loss based on a subjective (e.g., or subjective by proxy) metric may use Generative Adversarial Networks (GANs) during the training stage and / or advanced visual metric via a proxy NN.

[0141] In the autoencoder based compression system illustrated in FIGs.5 and / or 6, the entropy encoder and / or the decoder may rely on a fully factorized prior (e.g., probability) model. One or more separate trained entropy models per channel of the latent may be configured and / or considered. The spatial and / or channel correlations in the latent ^^ may not be considered as the samples (e.g., each of the samples) are encoded using the same distribution, e.g., assuming that the samples are independent and / or identically distributed (i.i.d). After the processing by ^^, ^^ may not identically distributed (i.i.d).

[0142] FIG.7 illustrates an example auto-encoder with a hyperprior approach. As illustrated in FIG.7, the model may include one or more additional convolutional sequences ^^and ^^. ^^may output one or more learned distribution parameters. For example, the one or more learned distribution parameters may be and / or may include one or more scales and / or means of Gaussian or Laplace distributions, e.g., for an element (e.g., for each element) of the latent ^^. The quantized tensor ^Ƹ, e.g., called the hyper latent, may output by ^^. For example, the quantized tensor ^Ƹ may need to be encoded and / or transmitted as side information for the decoder to decode ^^. Transmitting the hyper latent tensor ^Ƹ using a fully factorized probability model may not cost much overhead as ^Ƹ corresponds to ^ further downscaled by ^^and the efficiency of using tailored gaussian probability models for an element (e.g., each element) of the latent ^^ dramatically surpasses the burden of transmitting the light ^Ƹ.

[0143] FIG.7 may illustrate one or more operations and / or elements necessary for coding and / or decoding of an image. For example, the synthesis of the distribution information (e.g., scales and / or means) by ^^may appear at the encoder and / or the decoder. Like in video coding, the encoder may include one or more parts of the decoder to generate the exact same metadata that the decoder will decode, e.g., to process the rest of the bitstream (e.g., the video data). The synthesis ^^may perform one or more bit operations (e.g., one or more bitIDVC_2023P00829WO PATENT exact operations) between the encoder and the decoder for the system to work. A slight difference in the generated parameters may crash (e.g., completely crash) the arithmetic decoder for ^^.

[0144] Variable bitrate compression may be configured with an end-to-end learned image and / or video compression architecture.

[0145] Varying the compression ratio of an encoded content may be used for (e.g., be a requirement of) a lossy image and / or a lossy video compression system. In examples, an encoder may want to increase the compression ratio, e.g., to reduce the bitrate of the compressed bitstream (e.g., video data) to accommodate the transmission rate requirements of a communication medium. In examples, an encoder may want to decrease the compression ratio, e.g., to allow a decoder to reconstruct an image and / or a video content with a better visual quality (e.g., a lower distortion). The desired compression ratio and / or compression bitrate may be set, e.g., prior to starting the compression and / or during compression. For example, in a video compression application, a frame (e.g., each frame) of a content may need to be compressed with a different compression ratio (e.g., a slightly different compression ratio) to prevent large fluctuations of the bitrate and / or distortion in successive frames.

[0146] Not based on NN (e.g., traditional) image and / or video compression system may change a scalar parameter (e.g., a single scalar parameter) and / or a quantization step size, e.g., used in quantizing one or more (e.g., all) transform (e.g., or other representation) coefficients within the compression system. One or more other parameters within the compression system may be unchanged (e.g., may need not be changed). The method described herein may provide a simple and / or computationally efficient algorithm to vary the compression ratio. For example, the method described herein may provide an optimal or close-to-optimal tradeoff / change between the bitrate and distortion as the compression ratio is changed. The optimal or close- to-optimal tradeoff / change described herein may be due to the used transforms, e.g., called orthonormal transforms having one or more properties (e.g., one or more special properties).

[0147] In examples, while varying the compression ratio or bitrate may be performed using a simple and / or well-established method for an image and / or a video compression system (e.g., a traditional image and / or video compression system), an end-to-end learned image and / or a video compression system may not be configured as described herein (e.g., varying the compression ratio or bitrate). Varying the compression ratio may be performed by modifying one or more (e.g., all) weights of the NN in the system. Varying the compression ratio for the NN in the system may need to (e.g., require) retraining an entire system using a different ^ in the cost function.IDVC_2023P00829WO PATENT

[0148] As described herein, varying the compression ratio may be needed in a compression system and / or the end-to-end learned image compression system may use a set of NN weights (e.g., parameters) in the system. Using the set of NN weights (e.g., parameters) in the system may not be a feasible approach to varying the compression ratio. For example, varying the compression rate as described herein may need storing and / or loading one or more sets of NN weights to modify the compression ratio and / or bitrate. If a fine adjustment of the bitrate is desired, e.g., a feature of one or more video compression standards with around 50 values / choices for the quantization step size, one or more sets of NN weights may need to be stored and may be cumbersome (e.g., impractical). For an end-to-end learned image and / or video compression system, a set (e.g., a single set) of NN weights (e.g., models) may be configured and / or be used. If a set (e.g., a single set) of NN weights (e.g., models) is configured and / or used, one or more additional parameters may be modified to adjust the compression ratio and / or bitrate.

[0149] As described herein, a training algorithm may be configured and / or be used to obtain a set (e.g., a single set) of NN weights (e.g., a single model) for an end-to-end learned image and / or video compression system. Variable rate compression may be achieved with compression performance (e.g., better compression performance). Multi-objective optimization (MOO) algorithm and / or procedure may be configured and / or used. For example, MOO algorithm and / or procedure may be configured and / or used instead to and / or in addition to an objective (e.g., a single objective) optimization procedure.

[0150] As described herein, better variable rate learned image and / or video compression performance maty be obtained from a NN model (e.g., a single NN model).

[0151] One or more algorithms may be configured and / or used to achieve variable bitrate compression with a NN model (e.g., a single NN model).

[0152] In examples, a variable rate image compression framework based on a conditional autoencoder may be configured, e.g., instead of one or more convolution layers. For example, a conditional autoencoder may include one or more conditional convolution layers (e.g., conditioned on the cost adjustment parameter ^). The quantization step size may vary. For example, two parameters may be configured to vary a bitrate. The conditional convolution layers may be computationally complex. For example, the conditional convolution layers may be more computationally complex than one or more standard convolution layers and may be a complicated design and / or algorithm.

[0153] In examples, a variable rate image compression framework based on so-called gain units may be configured. Gain units may be multiplication factors per latent tensor channel. For example, a latent tensorIDVC_2023P00829WO PATENT channel may be multiplied by its own factor, e.g., before and / or after a rounding operation. The two factors may not be necessarily the inverses of each other as described herein: ^^,^,^ൌ ^^^^^^^^,^,^ڄ ^^^ (1) ^^^,^,^ൌ ^^,^,^ڄ ^^ᇱ(2)

[0154] In the equation (1), ^^,^,^may represent a latent variable (e.g., in channel ^ at horizontal position ^ and vertical position ^) output by an analysis function ^^of the learned compression system (e.g., as illustrated in FIG.7). ^^may be the gain and / or a factor for a channel ^ applied before rounding. ^^^^^^^ may be an operation of rounding a value to the nearest integer. ^^,^,^may be the resulting quantization index. In the equation (2), the reconstruction of the quantized value ^^^,^,^of the latent variable from the quantization index ^^,^,^may be performed by multiplying again with a Gain and / or factor ^^ᇱ, e.g., that may vary for a (e.g., each) channel ^.

[0155] To adjust the rate coarsely, a predefined set of 6 factors for a (e.g., each) ^^and / or ^^ᇱmay be learned for a (e.g., each) latent channel. To adjust the rate more finely, two of the predefined factors may be obtained (e.g., chosen) and may be interpolated (e.g., with an exponential interpolation) to obtain the gain units for the desired compression ratio and / or bitrate. The variable rate image compression framework based one or more gain units as described herein may have a simpler design and / or algorithm. For example, the variable rate image compression framework based one or more gain units as described herein may have a simpler design and / or algorithm than the variable rate image compression framework based on a conditional autoencoder described herein.

[0156] In examples, a variable rate image compression framework may be based on varying a parameter (e.g., a single parameter) and / or the quantization step size (e.g., that is used in quantizing a latent tensor variable, such as each latent tensor variable).

[0157] The equations (3) and (4) described herein may be an example case (e.g., a special case) of the equations (1) and (2) described herein. For example, if ^^^ ൌ^andൌ ^ are used in the equations (1) and (2), the equations (3) and (4) may be obtained. Note that ^ may be independent of the channel index ^. To adjust the rate, the quantization step size ^ may be varied. Using the equations (3) and (4) as described hereinIDVC_2023P00829WO PATENT may be similar to a method used in an image and / or video compression. The method described herein, e.g., using the equations (3) and (4), may provide a simple (e.g., simpler) design and / or algorithm.

[0158] As described herein, an additional parameter, such as a quantization offset, may be added in the quantization process used within a variable bitrate end-to-end learned image and / or video compression system. A variable rate end-to-end learned image and / or video compression framework based on varying two or more (e.g., two) parameters within the quantization operation of one or more latent variables ^^ may be configured. For example, the first parameter may be a scalar quantization step size ^, e.g., used in equations 3 and / or 4 and in an image and / or video compression system. The second parameter may be an accompanying quantization offset ^. The quantization operation may be achieved in two steps as follows: ^ ൌ௬^,^,ೕ^,^,^^^^^^^^^ (5)

[0159] In the equation (5), ^^,^,^may represent a latent variable (e.g., in a channel ^ at horizontal position ^ and vertical position ^) output by an analysis function ^^of a learned compression system (e.g., as illustrated in FIG.7). ^ may be a quantization step size. ^^^^^^^ may be an operation of rounding a value to the nearest integer. ^^,^,^may be the resulting quantization index. In the equation (6), the reconstruction of the quantized value ^^^,^,^of the latent variable, e.g., from the quantization index ^^,^,^, may be performed. ^^,^,^may be the quantization offset.

[0160] One or more algorithms may be configured to train a NN (e.g., a single NN) for variable bitrate compression.

[0161] As described herein, one or more latent tensor quantization algorithms may be configured to achieve variable bitrate image and / or video compression with an end-to-end learned NN model (e.g., set of NN weights). One or more NNs may be trained. A bitrate NN model (e.g., a single bitrate NN model) may be trained. The NN model (e.g., the single NN model) for variable bitrate compression may be trained.

[0162] One or more NN models that target a bitrate (e.g., a single bitrate) may be trained. For example, the one or more NN models that target a bitrate may be trained by using a cost function (e.g., a single cost function) and / or loss function as described herein. The loss function ^ may be or may include a Lagrangian form (e.g., ^ ൌ ^ ^ ^^). The training may be formulated as the following minimization of ^ with respect to theparameters ^ of the NN over a training set:Argmin ^^^^^ ^^^^^ (7)ఏIDVC_2023P00829WO PATENT

[0163] ^^^^ may represent the rate and / or bitrate. ^^^^ may represent the distortion of the decodedcontent. ^^^^and / or ^^^^may be functions of the NN parameters ^. ^ may be a factor that determines thetrade-off between rate and distortion. ^ may be the target bitrate. For every different target bitrate, a model (e.g., a new set of NN weights) may be trained with an appropriate ^ in the loss function. If an algorithm and / or a system uses NN models that target a bitrate (e.g., a single bitrate), in a practical compression application where the target bitrate needs to be changed, one or more NN models (e.g., sets of weights for the NN) may be stored (e.g., may need to be stored) at the encoder and / or the decoder.

[0164] Variable bitrate compression systems with a NN model (e.g., a single NN model), e.g., as described herein, may employ a slightly different training strategy. The variable bitrate compression systems may use a stochastic gradient descent-based training algorithm (e.g., a typical training algorithm in deep learning). The variable bitrate compression systems may choose a loss function (e.g., that is simply the sum of the loss functions coming from ^ different ^ values). The loss function may be chosen for a range of appropriate targetbitrates:

[0165] When calculating a loss ^^, a corresponding quantization parameter may be used, e.g., corresponding gains ^^in equations (1) and / or (2) or a corresponding ^ in equations (3) and / or (4). In addition to and / or alternative to using the sum as described herein, for a batch of the gradient descent-based training algorithm may choose the loss functions ^^at random.

[0166] A training procedure may be configured for a variable bitrate image and / or video compression system with a NN model (e.g., a single NN model). For example, a MOO may be used to obtain a set (e.g., single set) of NN weights (e.g., a single model), such that variable bitrate compression may perform better with the obtained model, e.g., compared to the model obtained by training the NN with an objective (e.g., a single objective) training algorithm. The MOO algorithm may provide a better training result, e.g., producing a model that is likely to provide better multi rate compression performance.

[0167] The MOO algorithm may be configured to train one or more NNs to fulfill one or more computer- related tasks (e.g., multi-task learning). As described herein, the MOO algorithm may be configured for variable bitrate image and / or video compression with a NN model (e.g., a single NN model).

[0168] One or more (e.g., two) possible parameter sets ^ and ^ҧfor the NN of a variable rate compression system may be obtained. The parameter sets may be configured such that ^^^^^ ^ ^^^^ҧ^ and ^^^^^ ^IDVC_2023P00829WO PATENT ^^^^ҧ^. In examples, for a target bitrate (e.g., one target bitrate), the parameter set ^ may provide a better compression result. In examples, for the other target bitrate, parameter set ^ҧmay provide a better compression result. To determine which parameter set is a better choice for the variable compression rate system may need weighting of the losses (e.g., an optimal weighting). The equations that includes the sum of losses ^^^^^may place equal importance on one or more (e.g., all) losses.

[0169] MOO may propose a formulation (e.g., an alternative formulation) to a variable bitrate end-to-end learned image and / or video compression. MOO may collect one or more objectives (e.g., one or more possibly conflicting objectives). For example, the loss functions ^^for one or more different target bitrates may beoptimized (e.g., optimized together) by using a vector-valued loss:argmin ^^^^^^^,^^^, ^ଶ^^^^,^ଶ^, … ^ே^^^^,^ே^^ (9)ఏ

[0170] One or more (e.g., all) parameters ^ of the NN may be divided into one or more groups. For example, one or more parameters ^ of the NN may be divided into two groups. ^^^may represent the one or more parameters of the NN that are shared and / or common if performing compression for a bitrate (e.g., typically a great majority of the NN parameters). ^^, ^ ൌ 1, … ,^ may represent the parameters that are target bitrate specific, e.g., used during compression for a particular (e.g., ^௧^) target bitrate. For example, for the image compression system as illustrated in FIG.7, ^^^may be and / or may include one or more (e.g., all) parameters and / or weights of ^^, ^^, ^^, ^^and / or the entropy bottleneck. ^^may be and / or may include a parameter such as the gains ^^in equations 3 and / or 4, the ^ in equations 5 and / or 6, or the ^ and / or offsets described herein.

[0171] A set of NN parameters ^ ൌ ^^^^,^^, … ,^ே^ may be configured. The set of NN parameters ^ ൌ ^^^^,^^, … ,^ே^ may achieve Pareto optimality as described herein:

[0172] A solution ^ ൌ ^^^^,^^, … , ^ே^ may dominate a solution ^ҧൌ ^^ҧ^^,^^ҧ, … ,^ҧே^ if ^^^^^^,^^^^^^^^ҧ^^,^^ҧ^ for one or more (e.g., all)

[0173] A solution ^כmay be Pareto optimal if a solution ^ does not dominate ^כ.

[0174] The MOO example described herein may be configured (e.g., solved) using one or more different optimization algorithms, e.g., including gradient based algorithms. For example, one or more gradient based MOO algorithms may be relevant (e.g., the most relevant ones) for variable bitrate compression system described herein. For example, one or more gradient based MOO algorithms may be relevant for variableIDVC_2023P00829WO PATENT bitrate compression system described herein since one or more NN training algorithms (e.g., one or more standard NN training algorithms) may be gradient based.

[0175] A multiple gradient descent algorithm (MGDA) may be configured (e.g., proposed) to solve one or more MOO examples described herein, e.g., using one or more gradients. For example, MGDA may beconfigured as the following:

[0176] The solution to the equation (10) may be 0. The ^ may be a Pareto stationary point (e.g., a locally Pareto optimal point) and / or the resulting solutionσே^ୀ^^^^ఏೞ^^^^^^^,^^^ may give a descent direction that improves one or more (e.g., all) losses ^^, ^ ൌ 1, … ,^. An algorithm for the MOO problem may be configured (e.g., proposed) as follows (e.g., ^^,^ଶ, … ,^ேoptimization may be obtained using a Frank-Wolfe procedure): Example Algorithm 1:

[0177] As described herein, the training of a NN (e.g., a single NN) for a variable bitrate image and / or video compression may be formulated as a MOO.

[0178] The algorithm 1 described herein may be used to solve the optimization example described herein (e.g., performing the training of the NN parameters). FIG.8 illustrates example comparisons between the end- to-end image compression procedure described herein and the variable bitrate compression framework, e.g., based on varying the ^ parameter. The first curve (e.g., the dash curve or hyperprior curve) may illustrate an example compression performance of a variable bitrate compression method (e.g., the default variable bitrateIDVC_2023P00829WO PATENT compression method) by using (e.g., training) 8 different NN weights and / or models. The second curve (e.g., the solid curve or Hyper+QVRF curve) may illustrate an example compression performance of variable bitrate compression by varying ઢ with a NN model (e.g., a single NN model) that is trained using a gradient descent training algorithm with a single loss defined as the sum of rate-distortion losses for multiple target bitrates. The third curve (e.g., the dash dot curve or the hyperprior fine curve) may illustrate an example compression performance of variable bitrate compression by varying ઢ with a NN model (e.g., a single NN model) that is trained using an MOO algorithm described herein. As illustrated in FIG.8, the second curve (e.g., the solid curve or Hyper+QVRF curve) may have better compression performance at lower bitrates. The third curve (e.g., the dash dot curve or the hyperprior fine curve) with the MOO algorithm descried herein may have better compression performance (e.g., catches up) at mid bitrates and may perform better at higher bitrates (e.g., with the gap between the two growing steadily with higher bitrates).

[0179] One or more training strategies may be configured (e.g., envisioned) to train an NN model (e.g., a single NN model) for variable rate image and / or video compression with the MOO algorithm described herein.

[0180] In examples, an end-to-end image and / or video compression system (e.g., an entire end-to-end image and / or video compression system) may be trained. For example, an end-to-end image and / or video compression system, such as the system illustrated in FIG.7, that includes one or more (e.g., all) shared subsystems ^_^, ^_^, ^_^, ^_^ and / or one or more target bitrate specific parameters, such as the Gains ^^as described herein(e.g., equations 3 and / or 4) or the quantization step size ^ as described herein (e.g., equations 5 and / or 6) or ^ and / or quantization offsets ^ described herein, and / or with the MOO algorithm example described herein.

[0181] In examples, an end-to-end pre-trained image and / or video compression system may be pre-trained. For example, an end-to-end pre-trained image and / or video compression system may be trained (e.g., pre- trained) with a value (e.g., a high value) of ^ in a cost function and / or with a cost function that includes sum of costs for one or more target bitrates (e.g., such as the upper-rightmost point of the dash curve or the hyperprior curve and / or the upper-rightmost point of the solid curve or Hyper+QVRF curve illustrated in FIG.8) and may be trained (e.g., further trained) and / or be fine-tuned with the MOO algorithm example as described herein.

[0182] Although features and elements are described above in particular combinations, one of ordinary skilled in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wirelessIDVC_2023P00829WO PATENT connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto- optical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

IDVC_2023P00829WO PATENT CLAIMS What is Claimed:

1. An apparatus comprising: a processor configured to: obtain a neural network (NN) model; obtain a first parameter and a second parameter, wherein the first parameter associated with a first compression bitrate and the second parameter is associated with a second compression bitrate; select a parameter to train the NN model, wherein the selection of the parameter is based on a multi-objective optimization (MOO) based algorithm, and wherein the parameter is one of the first parameter or the second parameter; and train the NN model based on the selected parameter.

2. The apparatus of claim 1, wherein the first compression bitrate comprises a range of bitrates and the second compression bitrate comprises a target bitrate.

3. The apparatus of claim 1 or claim 2, wherein the first parameter is associated with a set of parameters for a shared parameters that is associated with the range of bitrates and the second parameter is associated with a set of parameters that is associated with the target bitrate.

4. The apparatus of any one of claims 1-3, wherein the selected parameter is associated with a Pareto optimality.

5. The apparatus of any one of claims 1-4, wherein the selection of the parameter based on the MOO based algorithm comprises the processor being configured to: apply a gradient-based algorithm.

6. The apparatus of claim 5, wherein the gradient-based algorithm comprises a multiple gradient descent algorithm.IDVC_2023P00829WO PATENT 7. The apparatus of any one of claims 1-6, wherein the NN model is associated with at least one of a variable rate compression image system or a variable rate compression video system.

8. The apparatus of any one of claims 1-7, wherein the apparatus is a video encoding device.

9. The apparatus of any one of claims 1-7, wherein the apparatus is a video decoding device.

10. A method comprising: obtaining a neural network (NN) model; obtaining a first parameter and a second parameter, wherein the first parameter associated with a first compression bitrate and the second parameter is associated with a second compression bitrate; selecting a parameter to train the NN model, wherein the selection of the parameter is based on a multi-objective optimization (MOO) based algorithm, and wherein the parameter is one of the first parameter or the second parameter; and training the NN model based on the selected parameter.

11. The method of claim 10, wherein the first compression bitrate comprises a range of bitrates and the second compression bitrate comprises a target bitrate.

12. The method of claim 10 or claim 11, wherein the first parameter is associated with a set of parameters for a shared parameters that is associated with the range of bitrates and the second parameter is associated with a set of parameters that is associated with the target bitrate.

13. The method of any one of claims 10-12, wherein the selected parameter is associated with a Pareto optimality.

14. The method of any one of claims 10-13, wherein the selection of the parameter based on the MOO based algorithm comprises: applying a gradient-based algorithm.IDVC_2023P00829WO PATENT 15. The method of claim 14, wherein the gradient-based algorithm comprises a multiple gradient descent algorithm.

16. The method of any one of claims 10-15, wherein the NN model is associated with at least one of a variable rate compression image system or a variable rate compression video system.

17. The method of any one of claims 10-16, wherein the method is performed by a video encoding device.

18. The method of any one of claims 10-16, wherein the method is performed by a video decoding device.

19. A computer-readable medium comprising instructions for training a neural network model, the instructions causing one or more processors to perform the method of any one of claims 10-16.

20. Video data comprising information representative of a trained neural network model according to the method according to any one of claims 10-16.

Images