Temporal Attention-Based Neural Networks for Video Compression

Abstract

Systems, methods, and means are disclosed for video encoding and / or video decoding using artificial neural networks (e.g., convolutional neural networks or recurrent neural networks), attention, and / or attention with spatial attributes. For example, an apparatus may be configured to perform one or more of obtaining a context block, a current block, and a latent vector associated with the current block, performing at least one convolution on the context block, the reference block, and the latent vector, generating motion flow data associated with the current block based on the at least one convolution, or generating a bitstream including a representation of the motion flow data. The motion flow data may be quantized. The generated bitstream may include a representation of the quantized motion flow data.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Patent Application No. 63 / 291,642, filed December 20, 2021, the contents of which are incorporated herein by reference in their entirety. [Background technology]

[0002] Video coding systems may be used to compress digital video signals, for example to reduce the storage and / or transmission bandwidth required for such signals. Summary of the Invention [Problem to be solved by the invention]

[0003] Systems, methods, and means are disclosed for video encoding and / or video decoding using an artificial neural network (e.g., a convolutional neural network or a recurrent neural network), attention, and / or attention with spatial attributes. For example, a video encoding device may be configured to perform one or more of: obtaining a context block, a current block, and a latent vector associated with the current block; performing at least one convolution on the context block, the reference block, and the latent vector; generating motion flow data associated with the current block based on the at least one convolution, or generating video data including a representation of the motion flow data. The motion flow data may be quantized. The generated video data may include a representation of the quantized motion flow data.

[0004] For example, a latent vector associated with the context block may indicate attention to a context frame associated with the context block. The latent vector may be obtained using a context associated with the context block. The latent vector may be obtained using a weighted attention value associated with the context block. The weighted attention value associated with the context block may be obtained based on one or more attention values ​​of each block in the previously reconstructed blocks. Spatial feature extraction may be performed. For example, the spatial feature extraction may be performed using a Siamese network.

[0005] For example, the video decoding device may be configured to perform one or more of: obtaining encoded motion flow data (e.g., quantized motion flow data) associated with a current block; performing at least one deconvolution using a recurrent neural network on the encoded motion flow data; obtaining a predictive block for the current block based on the at least one deconvolution; or reconstructing the current block based on the predictive block and a residual. The deconvolution may be performed, for example, based on a latent vector associated with a context block. The latent vector may be obtained using a context associated with the context block. The latent vector may be obtained using a weighted attention value associated with the context block. The weighted attention value associated with the context block may be obtained based on the attention value of each block in the previously reconstructed blocks.

[0006] The systems, methods, and means may involve a decoder. In some embodiments, the systems, methods, and means described herein may involve an encoder. In some embodiments, the systems, methods, and means described herein may involve a signal (e.g., from an encoder and / or received by a decoder). A computer-readable medium may include instructions for causing one or more processors to perform the methods described herein. A computer program product may include instructions that, when executed by one or more processors, may cause the one or more processors to perform the methods described herein. [Brief description of the drawings]

[0007] [Figure 1A] FIG. 1A is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented. [Figure 1B] 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 one embodiment. [Figure 1C] 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 one embodiment. [Figure 1D] FIG. 1D is a system diagram illustrating a further exemplary RAN and a further exemplary CN that may be used within the communications system illustrated in FIG. 1A, according to one embodiment. [Diagram 2] FIG. 2 illustrates an exemplary block-based video encoder. [Diagram 3] FIG. 3 illustrates an exemplary video decoder. [Figure 4] FIG. 4 illustrates an example of a system in which various aspects and embodiments may be implemented. [Figure 5A] FIG. 5A illustrates an example of an end-to-end compression system. [Figure 5B] FIG. 5B illustrates an exemplary neural network architecture for encoding and decoding video. [Figure 6] FIG. 6 illustrates an example of reconstructing the residual using decoded motion information. [Figure 7] FIG. 7 illustrates an exemplary random access type temporal structure for efficient video coding. [Figure 8] FIG. 8 illustrates an example architecture with a recurrent convolution (Conv-LSTM) block denoted by fs. [Figure 9] FIG. 9 illustrates an exemplary attention architecture for frame xt-1. [Figure 10] FIG. 10 illustrates an exemplary calculation of attention ht-k with respect to ht-1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings, in which:

[0009] 1A is a diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. Communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcasts, etc., to multiple wireless users. Communications system 100 may enable multiple wireless users to access such content through sharing of system resources, including wireless bandwidth. For example, the communications system 100 may use 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.

[0010] 1A, communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, RAN 104 / 113, CN 106 / 115, public switched telephone network (PSTN) 108, Internet 110, and other networks 112, although it will be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a “station” and / or “STA,” may be configured to transmit and / or receive wireless signals, and may include user equipment (UE), mobile stations, fixed or mobile subscriber units, subscription-based units, paging, mobile phones, personal digital assistants (PDAs), smartphones, laptops, netbooks, personal computers, wireless sensors, hotspots or Mi-Fi devices, Internet of Things (loT) devices, watches or other wearable, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., for remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in an industrial and / or automated processing chain context), consumer electronics devices, devices operating in commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c, and 102d may be referred to interchangeably as a UE.

[0011] The communication system 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 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, an NR Node B, a site controller, an access point (AP), a wireless router, etc. Although the base stations 114a, 114b are each illustrated as a single element, it will be understood that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0012] 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), a relay node, 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 cells (not shown). These frequencies may be licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide wireless service coverage for a particular geographic area, which may be relatively fixed or may change over time. A cell may be further 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 transceiver for each sector of the cell. In one 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, using beamforming to transmit and / or receive signals in a desired spatial direction.

[0013] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d via 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).

[0014] More specifically, as noted above, the communications system 100 may be a multiple access system, but may use one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, the base stations 114a and the WTRUs 102a, 102b, 102c in the RAN 104 / 113 may implement a radio technology, such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 115 / 116 / 117 using wideband CDMA (WCDMA). WCDMA may include communications 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 ​​Uplink Packet Access (HSUPA).

[0015] In one 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).

[0016] In one embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology, such as New Radio (NR) radio access, which may establish the air interface 116 using NR technology.

[0017] In one 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, e.g., using dual connectivity (DC) principles. Thus, the air interface utilized by the 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., eNBs and gNBs).

[0018] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement a wireless technology such as IEEE 802.11 (i.e., Wireless Fidelity, WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access, WiMAX), CDMA2000, CDMA2000 1X, 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), or the like.

[0019] 1A may be, for example, a wireless router, a Home Node B, a Home eNode B, or an access point, but may utilize any suitable RAT to facilitate wireless connectivity in a localized area, such as a location of a business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, etc. 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 one 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 establish a picocell or a femtocell using a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.). 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 need to access the Internet 110 via the CN 106 / 115.

[0020] The RAN 104 / 113 may communicate with the CN 106 / 115, which may be any type of network configured to provide voice, data, application, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have various quality of service (QoS) requirements, such as, for example, different throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid 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 communicate directly or indirectly with other RANs that use 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 utilize NR radio technology, the CN 106 / 115 may also communicate with another RAN (not shown) using GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or WiFi radio technology.

[0021] The CN 106 / 115 may also act as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include a circuit-switched telephone network providing 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 transmission control protocol (TCP), user datagram protocol (UDP), and / or internet protocol (IP) of the TCP / IP Internet protocol suite. The networks 112 may include wired and / or wireless communication 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 use the same RAT as the RANs 104 / 113 or a different RAT.

[0022] 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 102c shown in FIG. 1A may be configured to communicate with a base station 114a, which may employ a cellular-based wireless technology, and a base station 114b, which may employ an IEEE 802 wireless technology.

[0023] 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1B, the WTRU 102 may include, among other things, 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. It will be understood that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0024] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. 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. Although FIG. 1B illustrates the processor 118 and the transceiver 120 as separate components, it will be understood that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0025] The transmit / receive element 122 may be configured to transmit or receive signals to or from a base station (e.g., 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 one 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.

[0026] 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.

[0027] The transceiver 120 may be configured to modulate signals transmitted by the transmit / receive element 122 and demodulate signals received by the transmit / receive element 122. As mentioned above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers to enable the WTRU 102 to communicate via multiple RATs, such as, for example, NR and IEEE 802.11.

[0028] The processor 118 of the WTRU 102 may be coupled to, and may receive user-entered data from, a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an 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 non-removable memory 130 and / or 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, etc. 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 home computer (not shown).

[0029] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control the power to other components in the WTRU 102. The power source 134 may be any suitable device for providing power to the WTRU 102. For example, the power source 134 may include one or more dry batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0030] The processor 118 may also be coupled to a 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, information from the GPS chipset 136, the WTRU 102 may receive location information from a base station (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may obtain location information by way of any suitable location determination method while remaining consistent with an embodiment.

[0031] 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 electronic compass, a satellite transceiver, a digital camera (for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, a Bluetooth® module, a frequency modulated (FM) radio 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, which 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.

[0032] The WTRU 102 may include a full-duplex radio where transmission and reception of some or all of the signals associated with a particular subframe (e.g., for both the UL (e.g., for transmission) and the downlink (e.g., for reception) may be parallel 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., via a separate processor (not shown) or via the processor 118). In one embodiment, the WRTU 102 may include a half-duplex radio for transmission and reception of either some or all of the signals (e.g., associated with a particular subframe for either the UL (e.g., for transmission) or the downlink (e.g., for reception)).

[0033] 1C is a system diagram illustrating the RAN 104 and the CN 106, according to one embodiment. As mentioned above, the RAN 104 may employ E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also communicate with the CN 106.

[0034] The RAN 104 may include eNodeBs 160a, 160b, 160c, although it will be understood that the RAN 104 may include any number of eNodeBs while remaining consistent with an embodiment. The eNodeBs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNodeBs 160a, 160b, 160c may implement MIMO technology. Thus, the eNodeB 160a may, for example, use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a.

[0035] Each of the eNodeBs 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, etc. As shown in FIG 1C, the eNodeBs 160a, 160b, 160c may communicate with one another via an X2 interface.

[0036] 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. Although each of the foregoing elements is illustrated as part of the CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0037] The MME 162 may be connected to each of the eNodeBs 162a, 162b, 162c in the RAN 104 via an S1 interface and may function as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, activating / deactivating bearers, selecting a particular serving gateway during initial attachment of the WTRUs 102a, 102b, 102c, etc. 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.

[0038] The SGW 164 may be connected to each of the eNodeBs 160a, 160b, 160c in the RAN 104 via an S1 interface. The SGW 164 may generally route and forward user data packets to and from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring the user plane during inter-eNodeB handover, triggering paging when DL data is available to the WTRUs 102a, 102b, 102c, and managing and storing the context of the WTRUs 102a, 102b, 102c.

[0039] The SGW 164 may be connected to a 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.

[0040] 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 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 other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0041] Although the WTRU is depicted in FIGS. 1A-1D as a wireless terminal, in certain representative embodiments, it is contemplated that such a terminal may use a wired communications interface (e.g., temporarily or permanently) with the communications network.

[0042] In an exemplary embodiment, the other network 112 may be a WLAN.

[0043] A WLAN in infrastructure Basic Service Set (BSS) mode may have an Access Point (AP) of the BSS and one or more stations (STAs) associated with the AP. The AP may have access or interface to a Distribution System (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic originating from outside the BSS to the STA may arrive through the AP and be delivered to the STA. Traffic originating from the STA to a destination outside the BSS may be sent to the AP and transmitted to the respective destination. Traffic between STAs within the BSS may be sent, for example, through the AP, where the source STA may send traffic to the AP, which may deliver the traffic to the destination STA. Traffic between STAs within the BSS may be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic may be sent between (e.g., directly between) the source STA and the destination STA using a direct link setup (DLS). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may be referred to herein as an "ad-hoc" communication mode.

[0044] When using an 802.11ac infrastructure mode of operation or a similar mode of operation, an AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., a 20 MHz wide bandwidth) or a width that is dynamically set via signaling. The primary channel may be the operating channel of the BSS, but may be used by STAs to establish a connection with the AP. In certain representative embodiments, for example, in an 802.11 system, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented. With CSMA / CA, STAs (e.g., all STAs), 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.

[0045] A High Throughput (HT) STA may use a 40 MHz wide channel for communication, which may be formed, for example, through a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels.

[0046] A Very High Throughput (VHT) STA may support 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. A 40 MHz and / or 80 MHz channel may be formed by combining multiple contiguous 20 MHz channels. A 160 MHz channel may be formed by combining eight 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, after channel encoding, the data may pass through a segment parser that may split the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time domain processing may be performed separately on each stream. The streams may be mapped to two 80 MHz channels and the data may be transmitted by the transmitting STA. At the receiver of the receiving STA, the operations described above for the 80+80 configuration may be reversed and the combined data may be transmitted to the Medium Access Control (MAC).

[0047] Sub-1 GHz operating modes are supported by 802.11af and 802.11ah. Channel operating bandwidths and carriers are reduced in 802.11af and 802.11ah compared to those used in 802.11n and 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 communication, such as MTC devices in macro coverage areas. MTC devices may have limited capabilities, including certain capabilities, for example, support for (e.g., support only for) certain and / or limited bandwidths. MTC devices may include batteries with above-threshold battery life (e.g., to maintain very long battery life).

[0048] WLAN systems that may support multiple channels and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, include a channel that may be designated as a primary channel. The primary channel may have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be configured and / or limited by the STAs among all STAs operating in the BSS that support the smallest bandwidth operating mode. In an 802.11ah example, the primary channel may be 1 MHz wide for STAs (e.g., MTC-type devices) that support (e.g., only) 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. For example, if the primary channel is active due to a STA (that only supports the 1 MHz mode of operation) transmitting to the AP, the entire available frequency band may be considered active even though most of the frequency band may remain dormant and available.

[0049] In the United States, the available frequency bands that can be used by 802.11ah are 902MHz to 928MHz. In South Korea, the available frequency bands are 917.5MHz to 923.5MHz. In Japan, the available frequency bands are 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz depending on the country code.

[0050] 1D is a system diagram illustrating the RAN 113 and the CN 115, according to one embodiment. As mentioned above, the RAN 113 may employ NR radio technology and communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also communicate with the CN 115.

[0051] The RAN 113 may include gNBs 180a, 180b, 180c, although it will be understood 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 an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, the gNBs 180a, 108b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a may transmit and / or receive wireless signals to and from the WTRU 102a, for example, using multiple antennas. In one 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 an unlicensed spectrum, while the remaining component carriers may be on a licensed spectrum. In one embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNBs 180a and 180b (and / or gNB 180c).

[0052] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with 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 the gNBs 180a, 180b, 180c using subframes or transmission time intervals (TTIs) of different or scalable lengths (e.g., including different numbers of OFDM symbols and / or lasting different lengths of absolute time).

[0053] 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 a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c without accessing another RAN (e.g., eNodeBs 160a, 160b, 160c, etc.). In a standalone configuration, the WTRUs 102a, 102b, 102c may utilize one or more of the gNBs 180a, 180b, 180c as mobility anchor points. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in unlicensed bands. In a non-standalone configuration, the WTRUs 102a, 102b, 102c may communicate with and connect to a gNB 180a, 180b, 180c while also communicating with and connecting to another RAN, such as an eNodeB 160a, 160b, 160c. For example, the WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNodeBs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNodeBs 160a, 160b, 160c may act as mobility anchors for the WTRUs 102a, 102b, 102c, and the gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for serving the WTRUs 102a, 102b, 102c.

[0054] 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 for network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data to User Plane Functions (UPFs) 184a, 184b, routing of control plane information to Access and Mobility Management Functions (AMFs) 182a, 182b, etc. As shown in FIG. 1D, the gNBs 180a, 180b, 180c may communicate with each other via an Xn interface.

[0055] 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. Although each of the foregoing elements is illustrated as part of the CN 115, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0056] 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 function as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, supporting network slicing (e.g., handling different PDU sessions with different requirements), selecting a particular SMF 183a, 183b, managing registration areas, terminating NAS signaling, mobility management, etc. The network slicing may be used by the AMF 182a, 182b to customize the CN support of the WTRUs 102a, 102b, 102c based on the type of service utilizing the 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, etc. 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.

[0057] The SMFs 183a, 183b may be connected to the AMFs 182a, 182b in the CN 115 via an N11 interface. The SMFs 183a, 183b may also be connected to the UPFs 184a, 184b in the CN 115 via an N4 interface. The SMFs 183a, 183b may select and control the UPFs 184a, 184b and configure the routing of traffic through the UPFs 184a, 184b. The SMFs 183a, 183b may perform other functions such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notification, etc. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0058] The UPFs 184a, 184b may connect 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 UPFs 184, 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, etc.

[0059] The CN 115 may facilitate communication with other networks. For example, the CN 115 may include or 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 other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to local data networks (DNs) 185a, 185b through the UPFs 184a, 184b via an N3 interface to the UPFs 184a, 184b and an N6 interface between the UPFs 184a, 184b and the DNs 185a, 185b.

[0060] 1A-1D and the corresponding description thereof, one or more or all of the functions described herein with respect to one or more of the WTRUs 102a-d, base stations 114a-b, eNode-Bs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a-b, SMFs 183a-b, DNs 185a-b, and / or any other devices 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.

[0061] The emulation device may be designed to implement one or more tests of other devices in a lab environment and / or an operator network environment. For example, one or more emulation devices may perform one or more or all functions while fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices in the communication network. One or more emulation devices may perform one or more or all functions while temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for testing purposes and / or may use terrestrial wireless communication to implement the tests.

[0062] The one or more emulation devices may perform one or more functions, inclusive, while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in test scenarios in a test lab and / or in an undeployed (e.g., test) wired and / or wireless communication network to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communication via RF circuitry (which may include, for example, one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0063] This application describes various aspects, including tools, features, examples, models, approaches, and the like. Many of these aspects are described with specificity and often in a potentially limiting manner to at least illustrate their individual characteristics. However, this is for purposes of clarity of description and does not limit the applicability or scope of the aspects. In fact, all of the different aspects may be combined and interchanged to provide further aspects. Moreover, aspects may similarly be combined and interchanged with aspects described in prior applications.

[0064] Aspects described and contemplated in this application may be implemented in many different forms. Figures 5-10 described herein may provide some examples, but other examples are contemplated. Discussion of Figures 5-10 is not intended to limit the scope of implementations. At least one of the aspects relates generally to video encoding and decoding, and at least one other aspect relates generally to transmitting a generated or encoded bitstream. 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 described methods, and / or a computer-readable storage medium having stored thereon a bitstream generated according to any of the described methods.

[0065] In this 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.

[0066] Various methods are described herein, each of which includes one or more steps or actions for achieving the described method. Unless a specific order of steps or actions is required for 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 embodiments to modify elements, components, steps, operations, etc., such as, for example, "first decode" and "second decode". The use of such terms does not imply any ordering to the modified operations, unless specifically required. Thus, in this embodiment, the first decode need not be performed before the second decode, but may occur, for example, before, during, or during an overlapping time with the second decode.

[0067] Various methods and other aspects described herein may be used to modify modules, such as the decoding modules, of the video encoder 200 and decoder 300, as shown in Figures 2 and 3. Moreover, the subject matter disclosed herein may apply to any type, format, or version of video coding, whether described in a standard or recommendation, whether existing or developed in the future, and to any extensions of such standards and recommendations, for example. Unless otherwise indicated or technically impossible, aspects described herein may be used individually or in combination.

[0068] Various numerical values ​​are used in the embodiments described in this application to illustrate the embodiments, and the aspects described are not limited to these specific values.

[0069] 2 illustrates an exemplary video encoder. Although variations of the exemplary encoder 200 are contemplated, the encoder 200 is described below for purposes of clarity without describing all possible variations.

[0070] Before being encoded, a video sequence may undergo pre-encoding processing (201), such as applying a color transformation to the input color picture (e.g., from RGB 4:4:4 to YCbCr 4:2:0) or performing a remapping of the input picture components to obtain a signal distribution that is more resilient to compression (e.g., using histogram equalization of one of the color components). Metadata may be associated with that pre-processing and attached to the bitstream.

[0071] In the encoder 200, a picture is coded by the encoder elements, as described below. The picture to be coded is divided (202) and processed, for example, in units of coding units (CUs). Each unit is coded, for example, using either intra mode or inter mode. When a unit is coded in intra mode, it performs intra prediction (260). In inter mode, motion estimation (275) and motion compensation (270) are performed. The encoder decides (205) whether to use intra mode or inter mode to code the unit, and indicates the intra / inter decision, for example, by a prediction mode flag. A prediction residual is calculated (210), for example, by subtracting the predicted block from the original image block.

[0072] The prediction residual is then transformed (225) and quantized (230). The quantized transform coefficients, as well as motion vectors and other syntax elements, are entropy coded (245) to output a bitstream. The encoder can skip the transform and apply quantization directly to the untransformed residual signal. The encoder can bypass both the transform and quantization, i.e., the residual is coded directly without applying a transform or quantization process.

[0073] The encoder decodes the coded block to provide a reference for further prediction. The quantized transform coefficients are dequantized (240) and inverse transformed (250) to decode the prediction residual. The decoded prediction residual and the predicted block are combined (255) to reconstruct an image block. An in-loop filter (265) is applied to the reconstructed picture to perform, for example, deblocking / Sample Adaptive Offset (SAO) filtering to reduce coding artifacts. The filtered image is stored in a reference picture buffer (280).

[0074] Figure 3 illustrates an embodiment of a video decoder. In the exemplary decoder 300, the bitstream is decoded by a decoder element as described below. The video decoder 300 generally performs a decoding path that is the inverse of the encoding path described in Figure 2. The encoder 200 also generally performs video decoding as part of encoding the video data.

[0075] Specifically, the decoder input includes a video bitstream, which may be generated by the video encoder 200. The bitstream is first entropy decoded (330) to obtain transform coefficients, motion vectors, and other coded information. Picture partition information indicates how the picture is partitioned. The decoder may then partition the picture according to the decoded picture partition information (335). The transform coefficients are inverse quantized (340) and inverse transformed (350) to decode the prediction residual. The decoded prediction residual and the predicted block are combined (355) to reconstruct an image block. The predicted block may be obtained from intra prediction (360) or from motion compensated prediction (i.e., inter prediction) (375) (370). An in-loop filter (365) is applied to the reconstructed image. The filtered image is stored in a reference picture buffer (380).

[0076] The decoded picture may further undergo post-decoding processing (385), such as an inverse color conversion (e.g., from YCbCr 4:2:0 to RGB 4:4:4) or inverse remapping that performs 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 embodiment, the decoded image (e.g., after application of an in-loop filter (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.

[0077] FIG. 4A illustrates an example of a system in which various aspects and embodiments described herein may be implemented. System 400 may be embodied as a device including various components described below and configured to perform one or more of the aspects described herein. Examples of such devices include various electronic devices, such as, but not limited to, personal computers, laptop computers, smartphones, tablet computers, digital multimedia set-top boxes, digital television receivers, personal video recording systems, connected appliances, and servers. The elements of system 400, singly or in combination, may be embodied in a single integrated circuit (IC), multiple ICs, and / or separate components. For example, in at least one embodiment, the processing and encoder / decoder elements of system 400 are distributed across multiple ICs and / or separate components. In various embodiments, system 400 is communicatively coupled to one or more other systems or other electronic devices, for example, via a communication bus or through dedicated input and / or output ports. In various embodiments, system 400 is configured to implement one or more of the aspects described herein.

[0078] The system 400 includes at least one processor 410 configured to execute instructions loaded therein, for example, to implement various aspects described herein. The processor 410 can include embedded memory, input / output interfaces, and various other circuits known in the art. The system 400 includes at least one memory 420 (e.g., a volatile memory device and / or a non-volatile memory device). The system 400 includes a storage device 440, which can 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 drives, and / or optical disk drives. Storage devices 440 may include, by way of non-limiting example, internal storage devices, attached storage devices (including removable and non-removable storage devices), and / or network-accessible storage devices.

[0079] The system 400 includes an encoder / decoder module 430 configured to process data to provide, for example, encoded or decoded video, which may include its own processor and memory. The encoder / decoder module 430 represents a module that may be included within a device to perform encoding and / or decoding functions. As is known, a device may include one or both of an encoding module and a decoding module. Additionally, the encoder / decoder module 430 may be implemented as a separate element of the system 400 or may be incorporated within the processor 410 as a combination of hardware and software, as is known to those skilled in the art.

[0080] Program code to be loaded into the processor 410 or the encoder / decoder 430 to implement various aspects described herein may be stored in the storage device 440 and then loaded onto the memory 420 for execution by the processor 410. According to various embodiments, one or more of the processor 410, the memory 420, the storage device 440, and the encoder / decoder module 430 may store one or more of various items during execution of the processes described herein. Such stored items may include, but are not limited to, input video, decoded video or portions of decoded video, bitstreams, matrices, variables, and intermediate or final results from processing of equations, expressions, operations, and operational logic.

[0081] In some embodiments, memory internal to the processor 410 and / or the encoder / decoder module 430 is used to store instructions and provide working memory for processing required during encoding or decoding. However, in other embodiments, memory external to the processing device (e.g., the processing device can be either the processor 410 or the encoder / decoder module 430) is used for one or more of these functions. The external memory can be the memory 420 and / or the storage device 440, e.g., dynamic volatile memory and / or non-volatile flash memory. In some embodiments, an external non-volatile flash memory is used, for example, to store the television's operating system. In at least one embodiment, a high-speed external dynamic volatile memory, such as a RAM, is used as working memory for video encoding and decoding operations.

[0082] Inputs to the elements of system 400 may be provided through a variety of input devices, as shown in block 445. Such input devices may include, but are not limited to, (i) a radio frequency (RF) section that receives, for example, RF signals transmitted over the air by a broadcast station, (ii) a component (COMP) input (or a set of COMP inputs), (iii) a universal serial bus (USB) input, and / or (iv) a high definition multimedia interface (HDMI) input. Other examples not shown in FIG. 4A include composite video.

[0083] In various embodiments, the input devices of block 445 have associated respective input processing elements as known in the art. For example, the RF section 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 frequency band), (ii) down-converting the selected signal, (iii) band-limiting again to a narrow frequency band to select a signal frequency band that may be referred to as a channel in a particular embodiment (e.g.), (iv) demodulating the down-converted band-limited signal, (v) performing error correction, and (vi) demultiplexing to select a desired stream of data packets. The RF section of various embodiments includes one or more elements for performing these functions, such as a frequency selector, a signal selector, a band limiter, a channel selector, a filter, a down-converter, a demodulator, an error corrector, and a demultiplexer. The RF section may include a tuner to perform various of these functions, including, for example, down-converting a received signal to a lower frequency (e.g., an intermediate frequency or a near-baseband frequency) or to baseband. In one set-top box embodiment, the RF section and its associated input processing elements receive RF signals transmitted over a wired (e.g., cable) medium and perform frequency selection by filtering, down-converting, and filtering again to a desired frequency band. Various embodiments rearrange the order of the above-described (and other) elements, remove some of these elements, and / or add other elements to perform similar or different functions. Adding elements may include inserting elements between existing elements, such as, for example, inserting amplifiers and analog-to-digital converters. In various embodiments, the RF section includes an antenna.

[0084] Additionally, the USB and / or HDMI terminals may include respective interface processors for connecting the system 400 to other electronic devices via USB and / or HDMI connections. It should be appreciated that various aspects of the input processing, e.g., Reed-Solomon error correction, may be implemented, for example, in a separate input processing IC or in the processor 410, as desired. Similarly, aspects of the USB or HDMI interface processing may be implemented, as desired, in a separate interface IC or in the processor 410. For example, the processor 410 and various processing elements, including an encoder / decoder 430, which operates in combination with memory and storage elements, to process the data stream as desired for presentation on an output device by providing a demodulated, error corrected, and demultiplexed stream to various processing elements, including an encoder / decoder 430, which operates in combination with memory and storage elements.

[0085] The various elements of system 400 may be provided within an integrated housing in which the various elements may be interconnected and transmit data between them using a suitable connection arrangement 425, such as an internal bus known in the art, including an Inter-IC (I2C) bus, hardwired, and printed circuit boards.

[0086] System 400 includes a communication interface 450 that enables communication with other devices over a communication channel 460. Communication interface 450 may include, but is not limited to, a transceiver configured to transmit and receive data over communication channel 460. Communication interface 450 may include, but is not limited to, a modem or a network card, and communication channel 460 may be implemented in a wired and / or wireless medium, for example.

[0087] Data is streamed or otherwise provided to system 400 in various embodiments using a wireless network such as a Wi-Fi network, e.g., IEEE 802.11 (IEEE refers to the Institute of Electrical and Electronics Engineers). The Wi-Fi signal in these embodiments is received via communication channel 460 and communication interface 450 adapted for Wi-Fi communication. Communication channel 460 in these embodiments is typically connected to an access point or router that provides access to external networks, including the Internet, to enable streaming applications and other over-the-top communications. Other embodiments provide streamed data to system 400 using a set-top box that provides data through an HDMI connection in input block 445. Still other embodiments provide streamed data to system 400 using an RF connection in input block 445. As noted above, various embodiments provide data in a non-streaming manner. Additionally, various embodiments use wireless networks other than Wi-Fi, e.g., a cellular network or a Bluetooth network.

[0088] The system 400 can provide output signals to various output devices including a display 475, speakers 485, and other peripheral devices 495. The display 475 in various embodiments includes, for example, one or more of a touch screen display, an organic light emitting diode (OLED) display, a curved display, and / or a foldable display. The display 475 can be for a television, a tablet, a laptop, a mobile phone, or other device. The display 475 can also be integrated with other components (e.g., as in a smart phone) or can be separate (e.g., an external monitor for a laptop). The other peripheral devices 495 in various embodiments include one or more of a stand-alone digital video disc (or digital versatile disc) (DVD for both terms), a disc player, a stereo system, and / or a lighting system. Various embodiments use one or more peripheral devices 495 that provide functionality based on the output of the system 400. For example, a disc player performs the function of playing the output of the system 400.

[0089] In various embodiments, control signals are communicated between system 400 and display 475, speaker 485, or other peripheral devices 495 using signaling such as AV.Link, Consumer Electronics Control (CEC), or other communication protocols that allow control between devices with or without user intervention. Output devices may be communicatively coupled to system 400 via dedicated connections through respective interfaces 470, 480, and 490. Alternatively, output devices may be connected to system 400 via communication interface 450 using communication channel 460. Display 475 and speaker 485 may be integrated into a single unit with other components of system 400 in an electronic device such as, for example, a television. In various embodiments, display interface 470 includes a display driver, such as, for example, a timing controller (T Con) chip.

[0090] Display 475 and speakers 485 may alternatively be separate 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 embodiments in which display 475 and speakers 485 are external components, output signals may be provided via dedicated output connections including, for example, an HDMI port, a USB port, or a COMP output.

[0091] These embodiments may be executed by the processor 410, or by computer software implemented by hardware, or by a combination of hardware and software. As a non-limiting example, these embodiments may be implemented by one or more integrated circuits. The memory 420 may be of any type suitable for the technology environment, and may be implemented using any suitable data storage technology, such as, as non-limiting examples, optical memory devices, magnetic memory devices, semiconductor-based memory devices, fixed memories, and removable memories. The processor 410 may be of any type suitable for the technology environment, and may include, as non-limiting examples, one or more of a microprocessor, a general-purpose computer, a special-purpose computer, and a processor based on a multi-core architecture.

[0092] Various implementations involve decoding. As used herein, "decoding" can encompass all or part of the processes performed on a received encoded sequence to result in a final output suitable for, e.g., a display. In various embodiments, such processing includes one or more of the processes typically performed by an encoder, such as, for example, dequantization, performing deconvolution, obtaining a prediction block, etc.

[0093] As a further example, in one embodiment, "decoding" refers to only entropy decoding, while in another embodiment, "decoding" refers to only differential decoding, while in another embodiment, "decoding" refers to a combination of entropy decoding and differential decoding. Whether the phrase "decoding process" is intended to refer to a task subset specifically or to the broader decoding process as a whole will be clear based on the context of the specific description and will be well understood by one of ordinary skill in the art.

[0094] Various implementations involve encoding. Similar to the above discussion of "decoding," "encoding" as used herein can encompass, for example, all or part of the processes performed on an input video sequence to produce an encoded bitstream. In various embodiments, such processes include one or more of the processes typically performed by an encoder, such as, for example, performing convolutions, obtaining latent vectors, motion flow data, etc.

[0095] As a further example, in one embodiment, "encoding" refers to only entropy encoding, while in another embodiment, "encoding" refers to only differential encoding, while in another embodiment, "encoding" refers to a combination of differential and entropy encoding. Whether the phrase "encoding process" is intended to refer to a task subset specifically or to the broader encoding process as a whole will be clear based on the context of the specific description and will be well understood by one of ordinary skill in the art.

[0096] It should be noted that the syntax elements used herein, e.g., latent vectors, attention values, etc., are descriptive terms and therefore do not preclude the use of other syntax element names.

[0097] Where a figure is presented as a flow diagram, it should be understood that the figure also provides a block diagram of the corresponding apparatus. Similarly, where a figure is presented as a block diagram, it should be understood that the figure also provides a flow diagram of the corresponding method / process.

[0098] The implementations and aspects described herein may be implemented, for example, in a method or process, an apparatus, a software program, a data stream, or a signal. Even if discussed in the context of only a single implementation form (e.g., discussed only as a method), the implementation of the discussed features may also be implemented in other forms (e.g., an apparatus or a program). An apparatus may be implemented, for example, in appropriate hardware, software, and firmware. The method may be implemented, for example, in a processor, where a processor generally refers to a processing device, and includes, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. Processors also include, for example, communication devices, such as computers, mobile phones, portable / personal digital assistants ("PDAs"), and other devices that facilitate communication of information between end users.

[0099] References to "one embodiment" or "an embodiment" or "one implementation" or "implementation," as well as other variations thereof, mean that a particular feature, structure, characteristic, etc. described in connection with an embodiment is included in at least one embodiment. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in one implementation" or "in an implementation" appearing in various places throughout this application, as well as any other variations thereof, are not necessarily all referring to the same embodiment.

[0100] Additionally, the application may refer to "determining" various information. Determining information may include, for example, one or more of estimating information, calculating information, predicting information, or retrieving information from a memory. Obtaining may include receiving, retrieving, constructing, generating, and / or determining.

[0101] Additionally, the application may refer to "accessing" various information. Accessing information may include, for example, one or more of receiving information, retrieving information (e.g., from a memory), storing information, moving information, copying information, calculating information, determining information, predicting information, or estimating information.

[0102] Additionally, the application may refer to "receiving" various information. Receiving, like "accessing," is intended to be a broad term. Receiving information may include, for example, one or more of accessing information or retrieving information (e.g., from a memory). Furthermore, "receiving" generally involves in some manner, for example, an operation such as storing information, processing information, transmitting information, moving information, copying information, erasing information, calculating information, determining information, predicting information, or estimating information.

[0103] For example, in the case of "A / B," "A and / or B," and "at least one of A and B," it should be understood that the use of any of the following " / ," "and / or," and "at least one of" is intended to encompass the selection of only the first listed alternative (A), or the selection of only the second listed alternative (B), or the selection of both alternatives (A and B). As a further example, in the case of "A, B, and / or C" and "at least one of A, B, and C," such language is intended to encompass the selection of only the first listed alternative (A), or the selection of only the second listed alternative (B), or the selection of only the third listed alternative (C), or the selection of only the first and second listed alternatives (A and B), or the selection of only the first and third listed alternatives (A and C), or the selection of only the second and third listed alternatives (B and C), or the selection of all three alternatives (A and B and C). This may be expanded as many times as the number of items listed, as would be apparent to one of ordinary skill in the art and related arts.

[0104] Also, as used herein, the term "signaling" specifically means to indicate something to a corresponding decoder. Encoder signals may include, for example, an indication of motion flow data, an indication of quantized motion flow data, etc. In this way, in one embodiment, the same parameters are used on both the encoder side and the decoder side. Thus, for example, the encoder may transmit a particular parameter to the decoder so that the decoder can use the same particular parameter (explicit signaling). Conversely, if the decoder already has the particular parameter as well as other parameters, it may use signaling without transmitting, simply to allow the decoder to know and select the particular parameter (implicit signaling). By avoiding transmitting any actual function, bit savings are realized in various embodiments. It should be understood that signaling may be achieved in various manners. For example, in various embodiments, one or more syntax elements, flags, etc. are used to signal information to a corresponding decoder. The above relates to the verb form of the word "signal", which may also be used as a noun in this specification.

[0105] As will be apparent to one of ordinary skill in the art, implementations may generate a variety of signals formatted to carry information that may be, for example, stored or transmitted. Information may include, for example, instructions for performing a method or data generated by one of the described implementations. For example, a signal may be formatted to carry a bit stream of the described embodiments. Such a signal may be formatted, for example, as an electromagnetic wave (e.g., using a radio frequency portion of the spectrum) or as a baseband signal. Formatting may include, for example, encoding a data stream and modulating a carrier wave with the encoded data stream. The signal that the signal carries may be, for example, analog or digital information. The signal may be transmitted by a variety of different wired or wireless links, as is known. The signal may be stored in, accessed from, or received from a processor-readable medium.

[0106] Many examples are described herein. The features of the examples may be provided alone or in any combination across various claim categories and types. Furthermore, an example may include one or more of the features, devices, or aspects described herein, alone or in any combination across various claim categories and types. For example, the features described herein may be embodied in a bitstream or signal that includes information generated as described herein. The information may enable a decoder to decode the bitstream, encoder, bitstream, and / or decoder according to any of the described embodiments. For example, the features described herein may be realized by generating and / or transmitting and / or receiving and / or decoding a bitstream or signal. For example, the features described herein may be realized as a method, a process, an apparatus, a medium that stores instructions, a medium that stores data, or a signal. For example, the features described herein may be implemented by a TV, a set-top box, a mobile phone, a tablet, or other electronic device that performs decoding. A TV, set-top box, mobile phone, tablet, or other electronic device may display (e.g., using a monitor, screen, or other type of display) the resulting image (e.g., an image from the residual reconstruction of the video bitstream). A TV, set-top box, mobile phone, tablet, or other electronic device may receive a signal that includes the encoded image and perform decoding.

[0107] Compression of video data may be performed, for example, using artificial neural network (ANN)-based tools. End-to-end deep video compression architectures (e.g., specialized in estimating motion flow relying on temporal structures) may be used. Attention-based recurrent neural network architectures may be used. For example, attention-based recurrent neural network architectures may enable capturing long-term and / or short-term dependencies between video frames. Capturing long-term and / or short-term dependencies between video frames may improve the approximation of motion flow information (e.g., motion vectors at each pixel location). Motion vectors may be estimated, for example, using one or more of the following: a recurrent neural network (e.g., incorporating convolution and / or deconvolution operations), an inter-frame attention block, or a feature extraction block (e.g., a Siamese feature extraction block). A recurrent neural network (e.g., incorporating a convolution operation) may enable capturing long-term and / or short-term motion information. A recurrent neural network (RNN) incorporating convolution operations can enable the use of variable input image / frame sizes. An inter-frame attention block can enable, for example, prioritization of motion vector estimation for a particular frame sequence. A feature extraction block (e.g., a Siamese feature extraction block) can enable, for example, preservation of spatial features of encoded video frames during attention computation.

[0108] ANN-based tools can be applied directly to end-to-end video compression models. ANN-based tools can, for example, use handcrafted prediction, transformation, and entropy coding tools (e.g., at the block level) to reduce (e.g., aim to reduce) redundancy. Attention mechanisms (e.g., as described herein) can replace or optimize motion estimation / compensation algorithms.

[0109] Image and video compression methods may use neural networks. ANN-based methods may use (e.g., rely on) parameters that are learned over a large data set during training (as opposed to traditional methods that may apply, e.g., hand-crafted prediction modes and transformations), for example, by iteratively minimizing a loss function. In a compression example, the loss function may describe an estimate of the bit rate of the encoded bitstream and / or an objective function for the decoded content. The quality of the reconstructed image may be optimized, for example, based on a measure of signal distortion or an approximation of visual quality (e.g., visual quality as perceived by humans).

[0110] 5A illustrates an exemplary end-to-end compression system. The inputs X to the encoder portion of the network may include one or more of an image or frame of video, a portion of an image, a tensor representing a group of images / frames, or a tensor representing a portion (e.g., a crop) of a group of images / frames.

[0111] The input may have one or more color components, for example monochrome, RGB, or YCbCr (YUV) components.

[0112] As shown in FIG. 5A, an input tensor X may be fed into an encoder network. The encoder network may include a sequence of convolutional layers (e.g., with nonlinear activation functions). Convolution and / or spatial-depth operations (e.g., large strides in the convolution and / or spatial-depth operations) may be used to, for example, reduce spatial resolution while increasing the number of channels. The encoder network may be (e.g., may be viewed as) a trained analytical transform.

[0113] 5A, the output of the encoder network (e.g., the "feature map" or "latent" Z) may be quantized and entropy coded (EC) as a binary stream (e.g., a bitstream) for storage or transmission. The output of the encoder network may include video data and / or video information.

[0114] As shown in FIG. 5A, the bitstream may be, for example,

[0115]

number

[0116] As shown in FIG. 5A, the decoder network

[0117]

number

[0118]

number

[0119] For example, a hyper-autoencoder (e.g., a hyper-prior) may be added to the network to learn (e.g., jointly learn) parameters of the latent distribution for efficient compression. End-to-end differentiable codecs (e.g., any end-to-end differentiable codec) may be considered.

[0120] Video compression using artificial neural networks may be performed. Figure 5B illustrates an exemplary neural network architecture for encoding and decoding video. The architecture may include, for example, an autoencoder that encodes different elements (e.g., elements required to reconstruct) for reconstructing a decoded video frame while removing inter-frame redundancy.

[0121] As shown in FIG. 5B, the I-frame block 510 may represent, for example, the encoding of an independently encoded (e.g., intra) key frame. In an embodiment, the I-frame block 510 and / or block-related processes described herein may be used (e.g., similarly) at the picture level, frame level, block level, slice level, tile level, sub-slice level, etc. The I-frame block 510 may include a simple autoencoder. The autoencoder may perform convolutional analysis and synthesis. Autoencoders may be developed for ANN-based image compression. An entropy coder (EC) and / or an entropy decoder (ED) may be used to remove redundancy (e.g., arithmetically remove redundancy), for example, in inference.

[0122] A neural network architecture (e.g., as shown in FIG. 5B) may be used to compress the video frames. Optical flow may be calculated (e.g., for the predicted frames). Optical flow may estimate motion flow (e.g., dense motion flow) between frames (e.g., each pixel location may be assigned a separate 2d motion vector, such as horizontal or vertical).

[0123] For example, the procedure described herein for the block level may be used at the frame level. A predicted frame (e.g., a P frame 520 as shown in FIG. 5B) may be encoded (e.g., as shown in FIG. 5B) if, for example, only one reference frame is used. At the encoder, the input is the current frame x cur and the previously reconstructed reference frame

[0124]

number

[0125]

number

[0126]

number

[0127]

number

[0128]

number

[0129]

number

[0130] FIG. 6 illustrates an example of reconstructing residuals using decoded motion information. Using ANN-based tools for video encoding and / or decoding may not be limited to the case of unidirectionally predicted frames. FIG. 7 illustrates an example random access type temporal structure for efficient video coding. ANN-based tools can be adapted and used for different temporal structures (e.g., random access group of pictures (GOP) structure as shown in FIG. 7, where the coding order can be modified such that most frames can be predicted using (e.g., multiple) already reconstructed past and / or future reference frames). As shown in FIG. 7, frames can be bi-predicted using past and future reference pictures (e.g., as shown by B frames in FIG. 7).

[0131] For example, if dependencies can be captured (e.g., by learning a latent representation of concatenated frames), then we can model the current frame x cur For,the reconstructed flow

[0132]

number

[0133]

number

[0134]

number

[0135]

number

[0136] The end-to-end architecture of the ANN may include one or more of the following: (e.g., efficient) encoding of time dependencies between frames, incorporating attention, or modeling attention (e.g., using spatial attributes).

[0137] For example, temporal dependencies between frames may be encoded. A recurrent neural network module (e.g., Conv-LSTM) may be used (e.g., at the decoder side of the architecture, as shown in FIG. 8) to keep state corresponding to the decoding of at least one previously decoded frame, for example, to account for temporality and redundancy between frames. Conv-LSTM can handle two-dimensional inputs and can capture and process 2d spatial information. Conv-LSTM blocks can handle input images of various sizes.

[0138] For example, attention can be incorporated into an exemplary end-to-end architecture of an ANN. Conv-LSTM and LSTM blocks can capture time dependencies. The attention mechanism can capture complex short-term and / or long-term time dependencies, for example, in tasks such as language translation (e.g., natural language processing). Using the attention mechanism can enable complex scene transitions and motion information to be coded (e.g., by a video compressor) more accurately and using fewer bits (e.g., compared to other approaches).

[0139] For example, modeling attention using spatial attributes may be performed. Modeling attention may be applied to text data. For example, the output of an LSTM cell may include a latent vector (e.g., a latent tensor or latent representation) that represents the context of a word. The output of an LSTM cell may be a matrix, which may be flattened into a one-dimensional vector.

[0140] Spatial context may be preserved. Preprocessing may be performed (e.g., before computing attention), for example, to preserve spatial attributes. Attention (e.g., in the context of natural language processing) may be used for word embeddings (e.g., which did not necessarily have any strong spatial features) as opposed to image / video cases. Spatial feature extraction may be performed before computing attention. A Siamese architecture may be used to perform spatial feature extraction before computing attention.

[0141] Long-term dependencies between frames can be captured and the reconstruction can be improved using, for example, one or more of the following: recurrent neural networks that capture long-term dependencies between frames and incorporate attention to provide weighted importance to certain intermediate frames:

[0142] RNN-based models (e.g., LSTMs and / or gated recurrent units (GRUs), etc.) may be used, for example, in the context of natural language processing. RNN-based models may be used, for example, to capture dependencies between words and / or sentences found in a line prior to a focus word (e.g., several lines prior to the focus word). RNNs may be integrated with (e.g., existing) ANN-based compression systems (e.g., as shown in FIG. 5B). Integrating RNNs with ANN-based compression systems may be challenging. RNN models may be (e.g., may be) designed for natural language processing, for example, where spatial aspects of data may be less important compared to temporal aspects. Capturing spatial features may be important for images. A (e.g., second) challenge in using RNNs (e.g., vanilla RNNs) may include the RNN's potential inability to handle various frame sizes. An exemplary RNN (e.g., where dense vector operations in LSTM cells are replaced with convolutions) may be used to overcome the problem of handling various frame sizes. An attention mechanism can be added to the recurrent block with (e.g., additional) Siamese sub-neural architectures, for example, to better capture spatio-temporal structures in the video.

[0143] Figure 8 shows the s 8 illustrates an example architecture with a recurrent convolution (e.g., Conv-LSTM) block denoted by: As shown in FIG. 8, the overall architecture of the model may include one or more of an I-frame autoencoder or a P-frame autoencoder.

[0144] The I-frame autoencoder may be, for example, a convolutional autoencoder (e.g., a pure convolutional autoencoder) that may be used to encode a frame (e.g., the first frame in a GoP). The encoding produced by the I-frame autoencoder may be large (e.g., in terms of bit size), for example, because the frame may be stand-alone compressed (e.g., there is no previous frame information to leverage). The I-frame autoencoder may include (e.g., only one) branch, which may be a standard convolutional image compressor (e.g., as shown in FIG. 8).

[0145] A P frame autoencoder (e.g., similar to that of FIG. 8) may include (e.g., two) separate branches: a branch for encoding and / or decoding motion information (e.g., as shown by the center branch in FIG. 8) and a branch for the residual (e.g., as shown by the right-most branch in FIG. 8).

[0146] Successive frames may be encoded in GoP using, for example, an I-frame autoencoder and / or a P-frame autoencoder, where the generated encoding can be made small by using (e.g., exploiting) spatio-temporal patterns in the video and pixel information from previously decoded frames. This is done by using the quantized motion tensor

[0147]

number

[0148]

number

[0149]

number

[0150] For example, for the current block, the corresponding context block in the context frame (e.g., the previous frame X t-1) may be obtained. A latent vector (e.g., a latent tensor, a latent representation) associated with the context block may be obtained. A convolution (e.g., at least one convolution) may be performed on the context block, the reference block, and the latent vector, e.g., to generate motion information (e.g., motion flow data) associated with the current block. The motion information (e.g., motion flow data) may be quantized, and a representation of the motion information (e.g., motion flow data) may be included, e.g., in the generated video data (e.g., in a bitstream).

[0151] For example, for a current block, encoded motion information (e.g., quantized motion information), such as motion flow data (e.g., quantized motion flow data), may be obtained. A deconvolution (e.g., at least one deconvolution) may be performed on the encoded motion information (e.g., encoded motion flow data). The deconvolution may be performed using a recurrent neural network (e.g., a motion decoder f s 8 with respect to . The predictive block associated with the current block may be obtained, for example, based on deconvolution. The current block may be reconstructed, for example, by combining the predictive block and the residual.

[0152] In an embodiment, the convolutions may be applied at different levels, such as at the picture, tile, slice, and / or coding block level. In an embodiment, the latent vectors may be applied at different levels, such as at the picture, tile, slice, and / or coding block level.

[0153] Motion Decoder sIn blocks, the spatial and temporal properties of the frame may be exploited using, for example, a convolution-based LSTM network (e.g., Conv-LSTM), which may avoid being limited by the spatial aspects of the video frame. A convolution-based LSTM network (e.g., Conv-LSTM) may determine the future state of a particular cell in the grid, for example, by the inputs and past states of its local neighbors. The input gate, forget gate, cell state, output, and hidden state of the ConvLSTM at a (e.g., particular) time instance t may be calculated using Equations 1-5, as described herein.

[0154]

number

[0155] for example, * may denote a convolution operator. For example,

[0156]

number

[0157]

number

[0158]

number

[0159]

number

[0160] The input to the residual branch is x t and warped

[0161]

number

[0162]

number

[0163]

number

[0164]

number

[0165] [Table 1]

[0166] Attention modeling can be performed. LSTMs can capture both long-term and short-term information over time. Attention can be used to improve LSTM performance for large time sequences. Attention can be applied in a variety of scenarios, for example, neural machine translation (NMT). These attentions can be applied across individual frame sequences over time.

[0167] Attention can create shortcuts between the context vector and the entire source input. The weights of these shortcut connections may be customizable for (e.g., each) output element. Customizing the weights of the shortcut connections for (e.g., each) output element may enable prioritization of the reconstruction of a frame (e.g., context) at time t using different weights for hidden states of past video frames. For example, emphasis may be placed on frames that can best predict the current frame (e.g., for random, complex motion like a scene cut).

[0168] Figure 9 shows frame x t-1 We illustrate an exemplary attention architecture for h t-1is the x from the LSTM (e.g., at time step t-1). t-1 The context frame x can represent the latent representation of t-1 The attention calculation for can be calculated using Equations 6 and 7 as follows:

[0169]

number

[0170] For example, h t-i h can be the hidden state (e.g., latent representation) for frame i={1,...,k} with a context window of size k. These may be provided by the output of the ConvLSTM. The pairwise dot product is t-1 ,The hidden states (e.g., all) of these past frames (e.g., h t-2 ,h t-k (e.g., followed by, for example, a Softmax operation to obtain the weights and / or attention of each past frame for the current frame being decoded (e.g., as shown in Equation 6). The hidden states may be input to an attention block (e.g., a trained attention block based on the trained parameters). The attention block may be used to perform a convolution on the input. The output of the attention block may include vectors and / or tensors. The output vectors and / or tensors may be weighted. The final weighted attention over the context frames is denoted by h t-1 (e.g., as shown by Equation 7) can be obtained by summing over the latent sequences weighted by their corresponding attention coefficients. t-1 x t-1 frame (e.g., frame x t-1 The weighted state may be the state associated with the best weighted state for a t-1 x t-1The final weighted attention over the context frames can be calculated as f s can be input to the block.

[0171] Spatial attributes can be preserved, for example, using a Siamese network. t-k Note about t-1 The exemplary computation of h is illustrated. The Siamese portion of the exemplary architecture can be expanded as shown in FIG. 10. The Siamese network can be a type of neural network in which parameters are shared. For example, t-k and h t-1 Both may be fed through the same neural network sharing the same convolution kernel, followed by flattening of the resulting feature representation. The hidden state may be passed through, for example, a Siamese sub-neural network to perform spatial feature extraction (e.g., since any spatial features may be lost during the flattening and dot product operations used (e.g., required) to compute similarity). The Siamese network may be a convolutional encoder in the main architecture.

[0172] Although the features and elements are described above in certain combinations, one skilled in the art will understand that each feature or element may 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 embodied in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random-access memory (RAM), registers, 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

1. 1. A video decoding device comprising a processor, the processor comprising: Obtaining encoded motion flow data associated with the current block; obtaining decoded motion flow data based on the encoded motion flow data and the latent vectors; generating a prediction block for the current block based on the decoded motion flow data; A video decoding device configured to reconstruct the current block based on the predictive block.

2. 1. A method comprising: Obtaining encoded motion flow data associated with a current block; obtaining decoded motion flow data based on the encoded motion flow data and the latent vectors; and generating a prediction block for the current block based on the decoded motion flow data; and and reconstructing the current block based on the predicted block.

3. The video decoding device of claim 1 or the method of claim 2, wherein the decoded motion data is obtained using deconvolution on the encoded motion flow data and the latent vectors.

4. 4. A video decoding device according to claim 1 or 3, wherein the deconvolution is performed using a recurrent neural network.

5. The processor, A video decoding device according to claim 1, further configured to concatenate the encoded motion flow data and the latent vector, wherein the decoded motion flow data is obtained based on the concatenated encoded motion flow data and the latent vector.

6. The processor, 6. The video decoding device of claim 1, further configured to obtain the latent vector associated with the current block based on state information associated with a previously reconstructed block.

7. The video decoding device of claim 6 , wherein the state information indicates a latent representation.

8. The processor, 6. The video decoding device of claim 1, further configured to obtain the latent vector associated with the current block based on state information associated with a plurality of previously reconstructed blocks.

9. The video decoding device of claim 8 , wherein the state information associated with a plurality of previously reconstructed blocks includes a latent representation of each of the plurality of previously reconstructed blocks.

10. The processor, 10. A video decoding device according to claim 1, further configured to obtain a weighted attention value associated with the current block, wherein the latent vector associated with the current block is obtained based on the weighted attention value associated with the current block.

11. The processor, 10. A video decoding device according to claim 1, further configured to obtain a plurality of attention values ​​for each block in a plurality of previously reconstructed blocks, wherein the weighted attention value associated with the current block is obtained based on the attention values ​​of the respective blocks in the plurality of previously reconstructed blocks.

12. 12. A video decoding device according to claim 1 or any one of claims 3 to 11, wherein the latent vector associated with the current block is configured to indicate an attention associated with the current block.

13. 1. A video encoding device, comprising: a processor, the processor comprising: Obtaining a reference block, a current block, and a latent vector associated with the current block; generating motion flow data associated with the current block based on the current block, the reference block, and the latent vector; A video encoding device configured to generate video data including a representation of the motion flow data.

14. 1. A method comprising: obtaining a reference block, a current block, and a latent vector associated with the current block; generating motion flow data associated with the current block based on the current block, the reference block, and the latent vector; generating video data comprising a representation of the motion flow data.

15. 15. The video encoding device of claim 13 or the method of claim 14, wherein the motion flow data is generated based on performing a convolution on the current block, the reference block and the latent vector.

16. The processor, 16. The video encoding device of claim 15, further configured to generate a latent representation of the current block for generating motion flow data associated with a second block based on the convolution performed on the current block.

17. 17. A video encoding device according to claim 12 or any one of claims 14 to 16, wherein the latent vector associated with the current block is obtained based on state information associated with a previously encoded block.

18. 17. A video encoding device according to claim 12 or any one of claims 14 to 16, wherein the latent vector associated with the current block is obtained based on state information associated with a number of previously encoded blocks.

19. The processor, 19. A video encoding device according to claim 12 or any one of claims 14 to 18, further configured to obtain a weighted attention value associated with the current block based on attention values ​​of respective blocks in a plurality of previously encoded blocks, wherein the latent vector associated with the current block is obtained based on the obtained weighted attention value associated with the current block.

20. 20. A video encoding device according to claim 12 or any one of claims 14 to 19, wherein the latent vector associated with the current block is configured to indicate an attention associated with the current block.

21. The processor, 21. A video encoding device according to claim 12 or any one of claims 14 to 20, further configured to perform a spatial feature extraction, and wherein the latent vector is obtained based on the performed spatial feature extraction.

22. A computer readable medium comprising instructions for causing one or more processors to perform the method of any one of claims 2 or 3 or 14 or 15.

23. A device, comprising: An apparatus according to any one of claims 1, 3 to 13 or 15 to 21, 1. A device comprising at least one of: (i) an antenna configured to receive a signal including data representing an image; (ii) a band limiter configured to limit the received signal to a frequency band including the data representing the image; or (iii) a display configured to display the image.

24. A signal comprising motion flow data generated using the reference blocks and the latent vectors according to the method of any one of claims 14 or 15.

25. 16. The method of claim 2 or 3 or 14 or 15, wherein the method is performed by a decoder or an encoder.

26. The device of any one of claims 1, 3-13 or 15-21, wherein the device comprises a memory.

Images