Old house renovation and decoration method and device, and storage medium

Abstract

The present disclosure provides a method and device for renovating and decorating an old house, and a storage medium. The method for renovating and decorating an old house includes: obtaining a three-dimensional house type model of the old house to be renovated according to a picture or video of the old house to be renovated, obtaining a two-dimensional model of the soft and hard decoration of the desired house to be renovated according to a picture or video of the desired house to be renovated, and combining the three-dimensional house type model of the old house with the two-dimensional model of the soft and hard decoration to obtain a target three-dimensional house type model. The technical solution realizes the application of image stylization technology in the field of renovation and decoration of old houses, provides a renovation and decoration solution for old houses, and the interactive mode of the renovation and decoration technology for old houses is simple and easy to operate.

Description

Technical Field

[0001] The disclosed embodiments relate to the field of real estate technology, and in particular to a method and device for renovating and decorating an old house, and a storage medium. Background Art

[0002] With the in-depth development of the real estate industry, the renovation and decoration industry of old houses has also been greatly developed, and the interactive demand for renovation and decoration of old houses has also been increasing. In the traditional renovation and decoration of old houses, the image stylization technology cannot be applied to the field of renovation and decoration of old houses, including but not limited to the inability to provide renovation and decoration solutions for old houses. In addition, the interactive mode of renovation and decoration technology of old houses is backward, lagging, and complicated, including but not limited to the need for users to have complex operation processes, non-real-time interaction, non-mobile interaction, and non-convenient interaction.

[0003] Therefore, there is an urgent need for a method of applying image stylization technology to the renovation and decoration of old houses.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a method and device for renovating and decorating an old house, and a storage medium, which at least to a certain extent solves the problem of how to apply image stylization technology to the renovation and decoration of an old house.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a method for renovating and decorating an old house is provided, comprising: obtaining a three-dimensional house type model of the old house to be renovated based on a picture or video of the old house to be renovated; obtaining a two-dimensional model of hard and soft furnishings of the house to be renovated based on a picture or video of the house to be renovated; and combining the three-dimensional house type model of the old house with the two-dimensional model of hard and soft furnishings to obtain a target three-dimensional house type model.

[0008] In an embodiment of the present disclosure, the method also includes: dismantling and modifying the three-dimensional apartment model of the old house to obtain a plurality of three-dimensional apartment models of the old house, and combining the three-dimensional apartment model of the old house with the two-dimensional model of hard and soft furnishings to obtain a target three-dimensional apartment model includes: combining a plurality of the three-dimensional apartment models of the old house with the two-dimensional model of hard and soft furnishings to obtain a plurality of target three-dimensional apartment models.

[0009] In an embodiment of the present disclosure, the demolition and modification of the old house three-dimensional apartment model to obtain a plurality of old house demolition and modification three-dimensional apartment models includes: establishing a graph convolutional network encoding layer; establishing a graph readout layer; and establishing an output layer.

[0010] In the disclosed embodiment, obtaining the three-dimensional floor plan model of the old house to be renovated based on the picture or video of the old house to be renovated includes: obtaining the two-dimensional floor plan model of the old house to be renovated based on the picture or video of the old house to be renovated; obtaining the three-dimensional floor plan model of the old house based on the two-dimensional floor plan model of the old house.

[0011] In an embodiment of the present disclosure, obtaining a three-dimensional model of hard and soft furnishings of the desired house based on a picture or video of the desired house includes: obtaining a two-dimensional model of hard and soft furnishings of the desired house based on a picture or video of the desired house; and identifying elements and attributes thereof based on the two-dimensional model of hard and soft furnishings.

[0012] In the disclosed embodiment, the combination of the multiple three-dimensional apartment models of the old house demolition and renovation and the two-dimensional models of the hard and soft furnishings to obtain multiple target three-dimensional apartment models includes: establishing a furniture selection intelligent agent; establishing a furniture placement intelligent agent; establishing a furniture movement actuator; looping the establishment of the furniture selection intelligent agent, the establishment of the furniture placement intelligent agent, and the establishment of the furniture movement actuator until the corresponding optimal three-dimensional apartment model is obtained; and designing the hard furnishings according to business rules to obtain multiple target three-dimensional apartment models.

[0013] In the disclosed embodiment, the method further includes: using a visualization engine to obtain video streams or photo streams corresponding to a plurality of target three-dimensional apartment models.

[0014] According to one aspect of the present disclosure, there is provided an old house renovation and decoration device, the device comprising: a first operation processing unit, used to obtain a three-dimensional house type model of the old house to be renovated according to a picture or video of the old house to be renovated; a second operation processing unit, used to obtain a two-dimensional model of hard and soft furnishings of the desired house to be renovated according to the picture or video of the desired house to be renovated; and a combination processing unit, used to combine the three-dimensional house type model of the old house with the two-dimensional model of hard and soft furnishings to obtain a target three-dimensional house type model.

[0015] According to one aspect of the present disclosure, there is provided an old house renovation and decoration device, the device comprising: at least one processor; and at least one memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-described old house renovation and decoration device methods by executing the executable instructions.

[0016] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, any one of the above-mentioned methods for renovating and decorating an old house is implemented.

[0017] In an embodiment of the old house renovation and decoration method disclosed in the present invention, a three-dimensional house type model of the old house to be renovated is obtained based on a picture or video of the old house to be renovated, a two-dimensional model of the soft and hard decoration of the desired house to be renovated is obtained based on a picture or video of the desired house to be renovated, and the three-dimensional house type model of the old house is combined with the two-dimensional model of the soft and hard decoration to obtain a target three-dimensional house type model. This technical solution realizes the application of image stylization technology in the field of old house renovation and decoration, provides a renovation and decoration solution for old houses, and the interaction mode of the renovation and decoration technology for old houses is simple and convenient to operate.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0020] Figure 1 A schematic diagram showing the process of the old house renovation and decoration method in the embodiment of the present disclosure;

[0021] Figure 2A Another schematic diagram showing the process of the old house renovation and decoration method according to the embodiment of the present disclosure;

[0022] Figure 2B A schematic diagram showing the old house renovation and decoration method in an embodiment of the present disclosure; and

[0023] Figure 3 The present invention is a schematic structural diagram of an old house renovation and decoration device according to at least one embodiment of the present invention. DETAILED DESCRIPTION

[0024] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0026] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making. Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level technology and software-level technology. Basic artificial intelligence technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0027] In view of the problem that the image stylization technology in the related art cannot be applied to the field of old house renovation and decoration, the present invention provides a method and device for old house renovation and decoration, and a storage medium. Through artificial intelligence technology, a three-dimensional house model of the old house to be renovated and a two-dimensional model of the soft and hard decoration of the desired house are combined to obtain a target three-dimensional house model, thereby realizing the application of image stylization technology in the field of old house renovation and decoration.

[0028] The disclosed embodiment provides a method for renovating and decorating an old house. Figure 1 The flowchart of the old house renovation method in the embodiment of the present disclosure is shown. Figure 1 As shown, the method includes steps S100 to S102.

[0029] S100, obtaining a three-dimensional house model of the old house to be renovated according to the picture or video of the old house to be renovated.

[0030] S101, obtaining a two-dimensional model of hard and soft decoration of a house to be decorated according to a picture or video of the house to be decorated.

[0031] S102, combining the old house three-dimensional apartment model with the two-dimensional models of hard and soft furnishings to obtain a target three-dimensional apartment model.

[0032] In the embodiment of the old house renovation and decoration method disclosed in the present invention, a 3D house type model of the old house to be renovated is obtained based on a picture or video of the old house to be renovated, a 2D model of the soft and hard decoration of the desired house to be renovated is obtained based on a picture or video of the desired house to be renovated, and the 3D house type model of the old house is combined with the 2D model of the soft and hard decoration to obtain a target 3D house type model. This technical solution realizes the application of image stylization technology in the field of old house renovation and decoration, provides a renovation and decoration solution for old houses, and the interaction mode of the renovation and decoration technology for old houses is simple and convenient to operate.

[0033] The disclosed embodiment provides a method for renovating and decorating an old house. Figure 2A Another schematic diagram of the process of renovating and renovating an old house in an embodiment of the present disclosure is shown. Figure 2A As shown, the method includes steps S200 and S204.

[0034] S200: Obtaining a three-dimensional house model of the old house to be renovated according to the picture or video of the old house to be renovated.

[0035] For example, a two-dimensional floor plan model of the old house to be renovated is obtained based on a picture or video of the old house to be renovated, and a three-dimensional floor plan model of the old house is obtained based on the two-dimensional floor plan model of the old house.

[0036] 1. Visualize and parse the old house to obtain a 2D picture of the old house. For example, parse the old house's video stream or picture stream to obtain a 2D picture of the old house.

[0037] 2. Use the CNN (convolutional) encoder to decode the 2D image into a 10x10x512 vector. The CNN decoder consists of 4 CNN (convolutional) layers with parameters of 160x160x128, 80x80x256, 40x40x512, and 20x20x512.

[0038] 3. Use the CNN (convolutional) decoder to decode the 10x10x512 vector output in 1-2 into a 128x128x3 vector. The CNN decoder consists of 2 layers of CNN (convolutional) layers to obtain the civil engineering (wall, door, window, top, floor, etc.) intent, and the parameters are: 20x20x512, 40x40x256.

[0039] 4. Detect the key points of each civil engineering element from the semantics, where the detection methods include but are not limited to (SSD detection method, FasterCNN detection method, etc.). The key points are the inflection points of each civil engineering element, and the contours of each civil engineering element are obtained from the inflection points.

[0040] 5. Calculate the length, width and height of each room based on the outline and get the 3D layout of the room.

[0041] S201, obtaining a two-dimensional model of hard and soft decoration of a house to be decorated according to a picture or video of the house to be decorated.

[0042] A two-dimensional model of the hard and soft furnishings of the desired house is obtained based on a picture or video of the desired house to be decorated, and each element and attribute thereof is identified based on the two-dimensional model of the hard and soft furnishings, for example, the elements and styles of the hard and soft furnishings are identified.

[0043] 1. Visualize and parse the old house to obtain a 2D picture of the old house. For example, parse the old house's video stream or picture stream to obtain a 2D picture of the old house.

[0044] 2. Detect and identify the soft furnishings and hard furnishings in the 2D image, and their attributes (size, color, category, style, etc.). For example, the soft furnishings and hard furnishings in the 2D image, and their attributes, are identified by using an SSD detection method or a FasterRCNN detection method, but the detection method is not limited to the SSD detection method and the FasterRCNN detection method.

[0045] S202, dismantling and modifying the three-dimensional apartment model of the old house to obtain a plurality of dismantling and modifying three-dimensional apartment models of the old house.

[0046] The demolition and modification of the three-dimensional apartment model of the old house to obtain a variety of demolition and modification of the three-dimensional apartment model of the old house includes: establishing a graph convolutional network encoding layer to determine a first eigenvector; establishing a graph readout layer to determine a second eigenvector; and establishing an output layer to determine a load-bearing wall.

[0047] 1. Create a 3D apartment plan into a diagram. The nodes of the diagram are civil engineering elements (walls, doors, windows, roofs, and ground). Each civil engineering element contains attributes (three-dimensional world position (x, y, z), three-dimensional world size (three-dimensional outline box), three-dimensional world orientation angle (a, b, c), category (wall: 1, door: 2, window: 3, roof: 4, ground: 5, etc.)), and the links between nodes are edges, where the edges are the distances between nodes in the three-dimensional world.

[0048] 2. Establish a graph convolutional network encoding layer, which includes 3 layers of graph convolution (GCN) with parameters (128, 256, 512, the number of graph convolution kernels), input the above-established graph, and output the first feature vector, such as a 512 vector.

[0049] 3. Establish a graph readout layer, which is obtained by two FC layers (fully connected layers) with parameters (512, 1024). The input is the above 512 vector and the output is the second eigenvector, for example, a 1024 vector.

[0050] 4. Establish the output layer to get the probability value of whether it is a load-bearing wall. The probability value range is 0-1. The larger the probability value, the greater the possibility of a load-bearing wall. Set a threshold for the probability value, and the wall with a probability value greater than the threshold is a load-bearing wall.

[0051] 5. Obtain N 3D apartment plans (N>=1), of which the first is the original apartment plan, and the second to Nth are apartment plans with non-load-bearing walls removed.

[0052] S203, combining a plurality of old house demolition and renovation three-dimensional apartment models with two-dimensional models of hard and soft furnishings to obtain a plurality of target three-dimensional apartment models.

[0053] The process of combining a variety of old house demolition and renovation three-dimensional apartment models with soft and hard decoration two-dimensional models is the process of automatic design of interior renovation, which mainly includes the following implementation methods.

[0054] 1. Build a furniture selection agent (agnet1), which consists of 3 convolutional layers (512x512x64, 256x256x128, 128x128x256) and 2 fully connected layers (256, M+1). The input is the top view of the current room, and the output is the probability (0-1) of putting a certain type of furniture in this state. There are M types of furniture in total. The probability value of the M+1 position is the largest.

[0055] 2. Create a furniture placement agent (agent2), which consists of 3 convolutional layers (512x512x64, 256x256x128, 128x128x256), 2 fully connected layers (256, 6), and the input is the top view of the current room and the selection of the Jth (J~(1, M)) type of furniture to be placed in the current room, as well as its initial state (the initial random position of the furniture), and moves this furniture. The output is a 6-bit vector, which represents the probability values ​​of the J type of furniture moving up, down, left, right, forward, and backward.

[0056] 3. Establish a furniture movement actuator, the input is the 4-bit probability value representing the movement of type J furniture, and the output is the movement in the direction of the maximum probability value.

[0057] 4. The steps of establishing a furniture selection agent, establishing a furniture placement agent, and establishing a furniture movement actuator are executed repeatedly until the probability values ​​of the M+1 position are both the maximum for the Nth and N+1th times. In the initial state, the room is empty, where the room is the N kinds of apartment plans outputted in step 202, and the furniture is the furniture outputted in step 201.

[0058] 5. Design hardware according to business rules.

[0059] 6. Output N design solutions corresponding to N apartment plans, for example, output N design solutions including soft furnishings and / or hard furnishings corresponding to N apartment plans, and the N apartment plans correspond to the N demolition and modification solutions output in step 202.

[0060] S204: Use a visualization engine to obtain video streams or photo streams corresponding to multiple target three-dimensional apartment models.

[0061] A visualization engine is used to obtain visualization of N design solutions. For example, video streams or photo streams of N design solutions are obtained through a UE engine or a vary engine. The visualization engine includes but is not limited to the above-mentioned UE engine and vary engine.

[0062] Figure 2B A schematic diagram showing the renovation method of an old house in an embodiment of the present disclosure is shown. Figure 2B As shown, the renovation and decoration method of the old house includes: visualization of the old house, establishment of the 3D house type of the old house, demolition and modification of the house type of the old house; visualization of expectations, identification of soft and hard decoration elements and styles; automatic interior design of the demolished and modified house type of the old house, and the identified soft and hard decoration elements and styles; visualization of the renovation of the old house.

[0063] The above steps S200 to S204 of the old house renovation and decoration method disclosed in the present invention are performed through a training model, and the training model may include three steps: initializing network parameters, gradient descent training and training cutoff.

[0064] 1. Initialize network parameters

[0065] The network parameters of the CNN (convolutional) encoder, CNN (convolutional) decoder, SSD / FasterRCNN network in step 200, the network for dismantling and modifying the old house floor plan in step 202, the network for furniture selection agent 1 in step 203, and the network for furniture selection agent 2 are randomly initialized. That is, the parameters of these networks are random.

[0066] 2. Gradient descent training

[0067] The error gradient of each sample and target is calculated during each training, and the network parameters of the CNN (convolution) encoder, CNN (convolution) decoder, SSD / FasterRCNN network in step 1, the network of the demolition and modification of the old house floor plan in step 202, the furniture selection agent 1 network, and the furniture selection agent 2 network in step 203 are calculated. Among them, the CNN (convolution) encoder and CNN (convolution) decoder in step 200 are training process 1 as a whole, and their target is the marked civil engineering language intent. The SSD / FasterRCNN network is training process 2, and its target is the inflection point in the marked civil engineering language intent. The SSD / FasterRCNN model in step 201 can use an existing public model. The graph network in step 202 is training process 3, and the target is the non-load-bearing wall in the marked floor plan. Step 203 is training process 4 for the selection agent 1 network and the furniture selection agent 2 network as a whole. The target is the marked furniture position, and the score is calculated as the overlapping IOU of the moved furniture position and the marked furniture position.

[0068] 3. Training deadline

[0069] After all samples in the data set have been fully trained each time, the average score of all samples in the data set is obtained. When the average score of the obtained data set is greater than 95 points after the Nth and N+1th trainings and remains unchanged, the training is stopped and the network parameters are stopped. If the training ends, there are 4 training processes 1-4, and the score calculation is as above. The target is completely different from the existing target and is 0, and it is completely the same as 100.

[0070] In the embodiment of the old house renovation and decoration method disclosed in the present invention, the old house three-dimensional house type model is dismantled and modified to obtain a variety of old house demolition and modification three-dimensional house type models, and the various old house demolition and modification three-dimensional house type models are combined with the soft and hard decoration two-dimensional models to obtain a variety of target three-dimensional house type models. This technical solution realizes the application of image stylization technology in the field of old house renovation and decoration, provides a renovation and decoration scheme for old houses, and the interaction mode of the old house renovation and decoration technology is simple and convenient to operate.

[0071] It should be noted that the old house renovation and decoration method of the embodiment of the present disclosure can be implemented through similar artificial intelligence methods, for example, through other CNNs, graph convolution, reinforcement learning, and machine learning.

[0072] At least one embodiment of the present disclosure provides a device for renovating and decorating an old house. Figure 3 This is a schematic diagram of the structure of an old house renovation and decoration device according to at least one embodiment of the present disclosure. Figure 3As shown, the old house renovation and decoration device 300 includes a first operation processing unit 301 for obtaining a three-dimensional house type model of the old house to be renovated according to a picture or video of the old house to be renovated; a second operation processing unit 302 is used to obtain a two-dimensional model of hard and soft furnishings of the desired house to be renovated according to the picture or video of the desired house to be renovated; and a combination processing unit 303 is used to combine the three-dimensional house type model of the old house with the two-dimensional model of hard and soft furnishings to obtain a target three-dimensional house type model.

[0073] The old house renovation and decoration device 300 corresponds to the old house renovation and decoration device in the method embodiment, and the old house renovation and decoration device 300 can be the old house renovation and decoration device in the method embodiment, or a chip or functional module inside the old house renovation and decoration device in the method embodiment. The corresponding units of the old house renovation and decoration device 300 are used to execute the corresponding steps executed by the old house renovation and decoration device in the method embodiment shown in FIG.

[0074] The old house renovation and decoration device 300 may also include a storage unit for storing data and / or signaling. The first operation processing unit 301, the second operation processing unit 302, the combination processing unit 303 and other units may interact or couple with the storage unit, for example, read or call the data and / or signaling in the storage unit, so that the method of the above embodiment is executed.

[0075] The above units can exist independently or be fully or partially integrated.

[0076] It should be noted that the old house renovation and decoration device can perform the above Figure 1 As for the renovation and decoration method for an old house shown in FIG2 , the relevant steps and features can be referenced to each other, and the technical principles and technical effects are similar, so they will not be repeated here.

[0077] At least one embodiment of the present disclosure provides an old house renovation and decoration device. The old house renovation and decoration device includes a processor and a memory. The memory is used to store executable instructions of the processor. The processor is configured to execute the above-mentioned Figure 1 The old house renovation and decoration method according to any one of the embodiments shown in FIG. 2 .

[0078] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0079] It can be understood that the memory in at least one embodiment of the present disclosure may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0080] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function according to at least one embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0081] At least one embodiment of the present disclosure further provides a computer-readable medium for storing computer program code, wherein the computer program includes instructions for executing the old house renovation and decoration method of at least one embodiment of the present disclosure in the above method. The readable medium may be a read-only memory (ROM) or a random access memory (RAM), which is not limited in at least one embodiment of the present disclosure.

[0082] At least one embodiment of the present disclosure further provides a computer program product, which includes a computer program / instruction, and the computer program / instruction is executed by a processor to perform instructions of the old house renovation and decoration method of at least one embodiment of the present disclosure in the above method. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section.

[0083] A program product for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0084] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0085] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0086] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0087] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0088] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0089] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0090] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0091] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A method for renovating and decorating an old house, characterized in that: include: Obtaining a three-dimensional house model of the old house to be renovated according to a picture or video of the old house to be renovated; Obtaining a two-dimensional model of the hard and soft furnishings of the desired house according to a picture or video of the desired house to be decorated; Combining the old house three-dimensional apartment model with the two-dimensional models of hard and soft furnishings to obtain a target three-dimensional apartment model; Wherein, obtaining a three-dimensional house type model of the old house to be renovated according to the picture or video of the old house to be renovated includes: Obtain a 2D picture of the old house from the visual analysis of the old house; use a CNN encoder to process the 2D picture of the old house to obtain the intent of civil engineering elements, wherein the civil engineering elements include at least one of the following: wall, door, window, roof, and floor; detect key points of each civil engineering element from the intent of the civil engineering element, wherein the key points are inflection points of each civil engineering element; obtain the outline of each civil engineering element from each inflection point; calculate the length, width, and height of each room from the outline, and obtain the 3D layout of the room; The step of combining the old house three-dimensional apartment model with the two-dimensional models of hard and soft furnishings to obtain a target three-dimensional apartment model includes: dismantling and modifying the old house three-dimensional apartment model to obtain a plurality of old house dismantling and modification three-dimensional apartment models, and combining a plurality of old house dismantling and modification three-dimensional apartment models with the two-dimensional models of hard and soft furnishings to obtain a plurality of target three-dimensional apartment models; The three-dimensional apartment model of the old house is demolished and modified to obtain a variety of three-dimensional apartment models of the old house, including: The 3D layout of the room is established into a graph; in the graph, each node is each of the civil engineering elements, each of the civil engineering elements includes a 3D world position, a 3D world size, a 3D world orientation angle, and a category, and the links of each node are edges, wherein the edges are the distances between each node in the 3D world; Establish a graph convolutional network encoding layer, input the graph, and output a first feature vector; establish a graph reading layer, input the first feature vector, and output a second feature vector; establish an output layer to obtain a probability value of whether it is a load-bearing wall; set a threshold value for the probability value, and determine that the wall with a probability value greater than the threshold value is a load-bearing wall; N kinds of 3D house type solutions are obtained, where N>=1, the first one is the original house type, and the second to N kinds are house type solutions with non-load-bearing walls removed; the N kinds of 3D house type solutions are used as the three-dimensional house type models for the demolition and reconstruction of the multiple old houses.

2. The method according to claim 1, characterized in that The demolition and modification of the old house three-dimensional apartment model to obtain a plurality of demolition and modification three-dimensional apartment models of the old house comprises: Establish a graph convolutional network encoding layer to determine the first eigenvector; Establishing a graph readout layer to determine a second eigenvector; and Create output layers to identify load-bearing walls.

3. The method according to claim 1, characterized in that The step of obtaining the three-dimensional apartment model of the old house to be renovated according to the picture or video of the old house to be renovated comprises: Obtaining a two-dimensional house model of the old house to be renovated according to a picture or video of the old house to be renovated; The three-dimensional apartment model of the old house is obtained according to the two-dimensional apartment model of the old house.

4. The method according to claim 1, characterized in that: The step of obtaining the soft and hard decoration three-dimensional model of the desired house according to the picture or video of the desired house includes: The method of obtaining a two-dimensional model of the hard and soft furnishings of the desired house according to the picture or video of the desired house to be decorated; The elements and attributes of the hardware and software two-dimensional models are identified.

5. The method according to claim 1, characterized in that The combining of the multiple three-dimensional house type models of the old house demolition and reconstruction with the two-dimensional models of the soft and hard decoration to obtain multiple target three-dimensional house type models includes: Building a furniture selection agent; Build a furniture placement agent; Building furniture movement actuators; Circularly executing the steps of establishing the furniture selection agent, establishing the furniture placement agent, and establishing the furniture movement actuator until a corresponding optimal three-dimensional apartment model is obtained; and Design the hard decoration according to business rules to obtain various target three-dimensional apartment models.

6. The method according to claim 5, characterized in that The method further comprises: Use the visualization engine to obtain video streams or photo streams corresponding to multiple target three-dimensional apartment models.

7. An old house renovation and decoration device, characterized in that: The device comprises: A first operation processing unit is used to obtain a three-dimensional apartment model of the old house to be renovated according to a picture or video of the old house to be renovated; A second operation processing unit is used to obtain a two-dimensional model of the hard and soft decoration of the house to be decorated according to the picture or video of the house to be decorated; A combination processing unit, used for combining the old house three-dimensional apartment model with the two-dimensional model of soft and hard furnishings to obtain a target three-dimensional apartment model; The first operation processing unit obtains a three-dimensional apartment model of the old house to be renovated according to the picture or video of the old house to be renovated, including: Obtain a 2D picture of the old house from the visual analysis of the old house; use a CNN encoder to process the 2D picture of the old house to obtain the intent of civil engineering elements, wherein the civil engineering elements include at least one of the following: wall, door, window, roof, and floor; detect key points of each civil engineering element from the intent of the civil engineering element, wherein the key points are inflection points of each civil engineering element; obtain the outline of each civil engineering element from each inflection point; calculate the length, width, and height of each room from the outline, and obtain the 3D layout of the room; The combination processing unit combines the old house three-dimensional apartment model with the two-dimensional model of hard and soft furnishings to obtain a target three-dimensional apartment model, including: dismantling and modifying the old house three-dimensional apartment model to obtain a plurality of old house dismantling and modifying three-dimensional apartment models, and combining a plurality of the old house dismantling and modifying three-dimensional apartment models with the two-dimensional model of hard and soft furnishings to obtain a plurality of target three-dimensional apartment models; The combination processing unit dismantles and modifies the old house three-dimensional apartment model to obtain a plurality of old house dismantling and modification three-dimensional apartment models, including: The 3D layout of the room is established into a graph; in the graph, each node is each of the civil engineering elements, each of the civil engineering elements includes a 3D world position, a 3D world size, a 3D world orientation angle, and a category, and the links of each node are edges, wherein the edges are the distances between each node in the 3D world; Establish a graph convolutional network encoding layer, input the graph, and output a first feature vector; establish a graph reading layer, input the first feature vector, and output a second feature vector; establish an output layer to obtain a probability value of whether it is a load-bearing wall; set a threshold value for the probability value, and determine that the wall with a probability value greater than the threshold value is a load-bearing wall; N kinds of 3D house type solutions are obtained, where N>=1, the first one is the original house type, and the second to N kinds are house type solutions with non-load-bearing walls removed; the N kinds of 3D house type solutions are used as the three-dimensional house type models for the demolition and reconstruction of the multiple old houses.

8. An old house renovation and decoration device, characterized in that: The device comprises: at least one processor; and at least one memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the old house renovation and decoration device method described in any one of claims 1 to 7 by executing the executable instructions.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by the processor, the old house renovation and decoration method described in any one of claims 1 to 7 is implemented.

Images