Data compression and decompression method and system, equipment and storage medium
By setting the predicted value of the tile in the color buffer in the GPU, the data compression method of the color buffer in the GPU is solved, and the memory access pressure caused by frequent reading and writing of tile in the GPU is realized, efficient data compression and decompression processing is achieved, and it is suitable for scenarios where local pixel blocks are frequently modified in the GPU.
Patent Information
- Application Number
- CN202411855317.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2025-03-28
AI Technical Summary
When rendering images, GPU frequently performs random and irregular read and write operations on the same tile in the color buffer, resulting in high memory access pressure and becoming a bottleneck in the system performance. The existing lossless image compression scheme is not suitable for scenarios in GPUs where local pixel blocks are frequently modified.
A data compression method is adopted to realize lossless compression and decompression of tile by setting prediction value, differential calculation and multi-level partition coding on the pixels in the block of the color buffer. The specific steps include: using the RGB and Alpha values of adjacent compressed pixels as predicted values, performing differential calculations of the Alpha and RGB channels, and finally performing multi-level partition encoding storage.
It significantly reduces the compressed encoded data and improves the compression ratio. It is suitable for scenarios where frequent reading and writing are performed in GPUs. The algorithm is simple and efficient, easy to implement with low latency.
Smart Images
Figure CN119728979A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular, to a data compression and decompression method, system, device and storage medium. Background Art
[0002] In the field of GPU and other chip design, memory access is often the bottleneck of system performance. Improving memory access efficiency is of great significance to improving chip performance. Frequent reading and writing of color buffer data has a great impact on performance. Color buffer data is generally stored in blocks, and the image is divided into several tiles.
[0003] The GPU also accesses the color buffer in units of tiles. When rendering an image, the same tile is frequently read and written, and the access to the tile is random and disordered, which makes the memory access pressure very high and becomes the performance bottleneck of the system. In order to reduce the amount of memory access data, the tile needs to be losslessly compressed and decompressed, and the algorithm needs to be simple and efficient, easy to implement in hardware, and have low latency.
[0004] Existing image lossless compression schemes usually target the entire image and are not suitable for scenarios where local pixel blocks need to be frequently modified in the GPU. Summary of the invention
[0005] In order to solve one of the above-mentioned technical defects, a data compression and decompression method, device and storage medium are provided in an embodiment of the present application.
[0006] According to a first aspect of an embodiment of the present application, a data compression method is provided, the method comprising:
[0007] For the pixel to be compressed in the block of the color buffer, the RGB value and the Alpha value of the adjacent compressed pixel are used as the prediction value of the pixel to be compressed in the RGB channel and the Alpha channel; the preset RGB channel reference value and the Alpha channel reference value are used as the prediction value of the RGB channel and the Alpha channel of the first pixel in the block;
[0008] For the pixels to be compressed, the difference between the actual Alpha value and the predicted value is calculated in the Alpha channel to obtain the Alpha difference value; the difference between the actual RGB value and the predicted value is calculated in the RGB channel to obtain the RGB difference value;
[0009] The RGB channel reference value, the Alpha channel reference value, the Alpha difference value, and the RGB difference value are stored in a multi-level partition encoding to compress the block.
[0010] In an optional embodiment of the present application, for the pixel to be compressed, performing a differential calculation between an actual Alpha value and a predicted value in an Alpha channel to obtain an Alpha differential value; performing a differential calculation between an actual RGB value and a predicted value in an RGB channel to obtain an RGB differential value further includes:
[0011] The difference calculation of the RGB channels includes first-order difference calculation and second-order difference calculation, and the RGB difference value is the second-order difference value.
[0012] In an optional embodiment of the present application, the step of performing multi-level partition encoding and storage of the RGB channel reference value, the Alpha channel reference value, the Alpha difference value, and the RGB difference value to compress the block further includes:
[0013] The Alpha difference value and its bit width encoding, and the RGB difference value and its bit width encoding are partitioned and stored separately.
[0014] According to a second aspect of an embodiment of the present application, a data decompression method is provided, the method comprising:
[0015] Extracting a multi-level partition code of pixel data in a block including a color buffer, wherein the multi-level partition code includes an alpha difference value and an RGB difference value of pixels in the block;
[0016] By using a differential algorithm, the Alpha differential value and the RGB differential value are restored according to the RGB values and Alpha values of the adjacent decompressed pixels, so as to obtain the RGB value and Alpha value of the pixel to be decompressed.
[0017] In an optional embodiment of the present application, the multi-level partition code of the pixel data in the block including the color buffer is extracted, and the step of extracting the alpha difference value and the RGB difference value of the pixel in the block included in the multi-level partition code further includes:
[0018] The multi-level partition coding also includes the bit width coding of the Alpha difference value and the bit width coding of the RGB difference value of the pixels in the block.
[0019] In an optional embodiment of the present application, the multi-level partition code of the pixel data in the block including the color buffer is extracted, and the step of extracting the alpha difference value and the RGB difference value of the pixel in the block included in the multi-level partition code further includes:
[0020] The RGB difference value is a second-order difference value.
[0021] According to a third aspect of the embodiment of the present application, a data compression system is provided, the system comprising a prediction module, a difference module and an encoding module; wherein:
[0022] The prediction module is used for predicting the RGB channel and the Alpha channel of the pixel to be compressed in the block of the color buffer using the RGB value and the Alpha value of the adjacent compressed pixel as the predicted value of the pixel to be compressed in the RGB channel and the Alpha channel; and using the preset RGB channel reference value and the Alpha channel reference value as the predicted value of the RGB channel and the Alpha channel of the first pixel in the block;
[0023] The difference module is used to perform a difference calculation between the actual Alpha value and the predicted value in the Alpha channel for the pixels to be compressed, and obtain the Alpha difference value; and perform a difference calculation between the actual RGB value and the predicted value in the RGB channel, and obtain the RGB difference value;
[0024] The encoding module is used to store the RGB channel reference value, the Alpha channel reference value, the Alpha difference value, and the RGB difference value in a multi-level partition encoding manner to compress the block.
[0025] According to a fourth aspect of the embodiment of the present application, a data decompression system is provided, the system comprising an extraction module and a restoration module; wherein:
[0026] An extraction module, used for extracting multi-level partition codes of pixel data in a block including a color buffer, wherein the multi-level partition codes include alpha difference values and RGB difference values of pixels in the block;
[0027] The restoration module is used to restore the Alpha difference value and the RGB difference value according to the RGB value and Alpha value of the adjacent decompressed pixels through a differential algorithm to obtain the RGB value and Alpha value of the pixel to be decompressed.
[0028] According to a fifth aspect of the embodiments of the present application, there is provided a computer device, including: a memory;
[0029] A processor; and a computer program; wherein the computer program is stored in a memory and is configured to be executed by the processor to implement a method as in any one of the first and second aspects of the embodiments of the present application.
[0030] According to the sixth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored; the computer program is executed by a processor to implement a method as in any one of the first and second aspects of the embodiments of the present application.
[0031] The data compression and decompression method provided in the embodiment of the present application has the following beneficial effects:
[0032] The present application can compress pixel blocks in the frame buffer, and is suitable for scenarios where blocks are frequently read and written in the GPU. In addition, the present application adopts a differential method, which can significantly reduce the compressed encoded data and improve the compression ratio. At the same time, the method is simple and efficient, and it is easy to obtain low-latency hardware implementation. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0034] Figure 1 is a flow chart of a data compression method provided in an embodiment of the present application;
[0035] Figure 2 This is a schematic diagram of prediction value selection provided in an embodiment of the present application;
[0036] Figure 3 is a schematic diagram of a differential calculation process provided in an embodiment of the present application;
[0037] Figure 4 It is a schematic diagram of the coding storage layout provided in an embodiment of the present application;
[0038] Figure 5 is a flow chart of a data decompression method provided in an embodiment of the present application;
[0039] Figure 6 is a structural diagram of a data compression system provided in an embodiment of the present application;
[0040] Figure 7 is a structural diagram of a data decompression system provided in an embodiment of the present application;
[0041] Figure 8 A schematic diagram of the computer device structure provided for one embodiment of the present application. DETAILED DESCRIPTION
[0042] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.
[0043] When a graphics processing unit (GPU) performs 3D rendering, the drawn image data is stored in memory, which is called a frame buffer. During the rendering process, the GPU frequently reads and writes the contents of the frame buffer until a frame of image is completed. This process involves a large number of memory access requests, so the GPU has very high requirements for memory access bandwidth.
[0044] The frame buffer is divided into several tiles according to the specified width and height. The GPU accesses the frame buffer in units of tiles. The frame buffer includes: color buffer, Z-buffer and template buffer. The frame buffer plays an important role in graphics rendering. It is used to store and manage various data in the rendering process, including pixel color information, depth information and template information.
[0045] The color buffer is used to store the color information of each pixel, which will eventually be displayed on the screen to achieve image presentation. In an embodiment of the present application, each pixel in the color buffer has four channels: Red (red component), Green (green component), Blue (blue component), and Alpha (opacity), all of which are 8-bit binary data. When the GPU accesses the color buffer, it uses tiles as units. Each tile consists of a pixel block with a width of W pixels and a height of H pixels, containing 4*W*H bytes of data. When the GPU reads the frame buffer, it reads the compressed data of a tile from the memory, and decompresses it to obtain the complete data of this tile; when the GPU writes the frame buffer, it compresses the data of a tile and then writes it to the memory.
[0046] Figure 1 For a flowchart of the data compression method provided in the embodiment of the present application, please refer to Figure 1 :
[0047] S11: For the pixel to be compressed in the block of the color buffer, the RGB value and the Alpha value of the adjacent compressed pixel are used as the prediction value of the pixel to be compressed in the RGB channel and the Alpha channel; the preset RGB channel reference value and the Alpha channel reference value are used as the prediction value of the RGB channel and the Alpha channel of the first pixel in the block.
[0048] In a specific implementation, the color values of adjacent pixels in the frame buffer are often close, so the predicted value Pred can be calculated based on the color values of the processed adjacent pixels, and this predicted value will be used for the next step of differential calculation. The more accurate the predicted value, the smaller the differential, and the better the encoding compression effect.
[0049] Specifically, a reference value is set for each of the RGB channel and the Alpha channel, and the reference value is used as the predicted value of the first pixel.
[0050] In the embodiment of the present application, the selection of the prediction value can be as follows: Figure 2 As shown in , for the first column of pixels, the color value of the adjacent pixel in the previous row is selected as the predicted value, and for other pixels, the color value of the adjacent pixel on the left is selected as the predicted value. Figure 2 As shown, for the P00 pixel, the reference value is used as the prediction value. In the first column, for the P10 pixel, the color value of the P00 pixel is used as the prediction value, and for the Ph0 pixel, the color value of the Pi0 pixel is used as the prediction value. In other columns, for the P01 pixel, the color value of the P00 pixel is used as the prediction value, for the P0w pixel, the color value of the P0j pixel is used as the prediction value, and for the Pij pixel, the color value of the adjacent pixel to its left is used as the prediction value.
[0051] S12: For the pixel to be compressed, a difference calculation is performed on the Alpha channel between the actual Alpha value and the predicted value to obtain the Alpha difference value; and a difference calculation is performed on the RGB channel between the actual RGB value and the predicted value to obtain the RGB difference value.
[0052] In some embodiments of the present application, the differential calculation of the RGB channels includes a first-order differential calculation and a second-order differential calculation, and the RGB differential value is a second-order differential value.
[0053] In the specific implementation, the RGB channel and the Alpha channel are processed separately. For the Alpha channel, the actual Alpha value of the current pixel, that is, the pixel to be compressed, is differentiated from the predicted value to obtain the difference Da of the Alpha channel. For the RGB channel, the RGB value of the current pixel, that is, the actual RGB value of the pixel to be compressed, is differentiated from the three corresponding channels of the predicted value Pred to obtain the result {Dr, Dg, Db}, and then the second-order difference Dgr = Dg-Dr and Dbg = Db-Dg are calculated.
[0054] like Figure 3 As shown, the encoded data size can be significantly reduced by second-order difference.
[0055] S13: RGB channel reference values, Alpha channel reference values, Alpha difference values, and RGB difference values are stored in a multi-level partition encoding to compress the block.
[0056] In some embodiments of the present application, the Alpha difference value and its bit width encoding, and the RGB difference value and its bit width encoding are partitioned and stored separately.
[0057] In the specific implementation, the difference result calculated in the previous step is subjected to multi-level partition encoding, and the Alpha channel and the RGB channel are also processed separately, such as Figure 4 As shown:
[0058] First, the reference value of the RGB channel (RGB Ref) and the reference value of the Alpha channel (Alpha Ref) are encoded as 24-bit and 8-bit binary data respectively, and stored in the first partition (Zone 1) and the second partition (Zone 2).
[0059] The bit width of Da (Alpha width) is encoded in the 4th zone (Zone 4), the value (Alpha value) is stored in the 5th zone (Zone 5), and the length of the 5th zone (Zone 5's Length) is stored in the 3rd zone (Zone 3).
[0060] Pack and encode {Dr, Dgr, Dbg} to obtain compressed data of the RGB channels, and store their bit width (RGB width) and value (RGB value) in the 6th partition (Zone 6) and the 7th partition (Zone 7) respectively.
[0061] Specifically, among the seven partitions, only the fifth and seventh partitions have variable lengths, while the lengths of the other partitions are fixed, which are determined by the size of the tile. If the difference value is 0, there is no need to store the value. For larger difference values, data needs to be stored in multiple partitions. Multi-level partition storage can reduce storage space and improve compression ratio.
[0062] Furthermore, the decompression process is the inverse process of the above compression process. First, the compressed code is extracted to obtain the differential value, and then the color value of the currently processed pixel is restored according to the differential algorithm and the decompressed adjacent pixel color value. This process has low complexity and can be implemented in hardware with low latency. Corresponding to the data compression method provided in the embodiment of the present application, Figure 5 For a flowchart of the data decompression method provided in the embodiment of the present application, please refer to Figure 5 :
[0063] S21: extracting the multi-level partition code of the pixel data in the block including the color buffer, wherein the multi-level partition code includes the Alpha difference value and the RGB difference value of the pixels in the block.
[0064] In some embodiments of the present application, the multi-level partition coding also includes Alpha differential value bit width coding and RGB differential value bit width coding of pixels within a block.
[0065] Furthermore, the RGB difference value is a second-order difference value.
[0066] S22: Using a differential algorithm, restore the Alpha differential value and the RGB differential value according to the RGB values and Alpha values of the adjacent decompressed pixels to obtain the RGB value and Alpha value of the pixel to be decompressed.
[0067] In summary, the embodiment of the present application compresses and decompresses pixel blocks in the frame buffer, which is suitable for the scene where blocks are frequently read and written in the GPU. In addition, the embodiment of the present application adopts second-order difference, which can significantly reduce the compressed encoded data and improve the compression ratio. At the same time, the algorithm is simple and efficient, and it is easy to obtain low-latency hardware implementation.
[0068] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
[0069] For the data compression method provided in the embodiment of the present application, see Figure 6 An embodiment of the present application provides a data compression system, which includes a prediction module 11, a difference module 21 and an encoding module 31; wherein,
[0070] The prediction module 11 is used for predicting the pixel to be compressed in the block of the color buffer using the RGB value and Alpha value of the adjacent compressed pixel as the predicted value of the pixel to be compressed in the RGB channel and the Alpha channel; and using the preset RGB channel reference value and the Alpha channel reference value as the RGB value and the Alpha value of the first pixel in the block;
[0071] The difference module 21 is used for performing a difference calculation between the actual Alpha value and the predicted value on the Alpha channel of the pixel to be compressed to obtain the Alpha difference value; performing a difference calculation between the actual RGB value and the predicted value on the RGB channel to obtain the RGB difference value;
[0072] The encoding module 31 is used to perform multi-level partition encoding and storage on the RGB channel reference value, the Alpha channel reference value, the Alpha difference value, and the RGB difference value to compress the block.
[0073] Corresponding to the data decompression method provided in the embodiment of the present application, further, see Figure 7 An embodiment of the present application provides a data decompression system, which includes an extraction module 12 and a restoration module 22; wherein,
[0074] An extraction module 12 is used to extract the multi-level partition code of the pixel data in the block containing the color buffer, wherein the multi-level partition code contains the Alpha difference value and the RGB difference value of the pixel in the block;
[0075] The restoration module 22 is used to restore the Alpha difference value and the RGB difference value according to the RGB value and Alpha value of the adjacent decompressed pixels through a differential algorithm to obtain the RGB value and Alpha value of the pixel to be decompressed.
[0076] For the specific definition of the above-mentioned data compression and decompression system, please refer to the definition of the data compression and decompression method above, which will not be repeated here. Each module in the above-mentioned data compression and decompression system can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0077] In one embodiment, a computer device is provided, the internal structure diagram of which can be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above data compression and decompression method is implemented. It includes: a memory and a processor, the memory stores a computer program, and the processor implements the above data compression and decompression method when executing the computer program.
[0078] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above data compression and decompression method can be implemented.
[0079] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, C language, VHDL language, Verilog language, object-oriented programming language Java and literal scripting language JavaScript, etc.
[0080] The present application is described with reference to the flowcharts and / or block diagrams of the systems and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0081] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0083] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0084] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A data compression method, characterized in that: include: For a pixel to be compressed in a block of the color buffer, the RGB value and the Alpha value of the adjacent compressed pixel are used as the prediction value of the pixel to be compressed in the RGB channel and the Alpha channel; the preset RGB channel reference value and the Alpha channel reference value are used as the prediction value of the RGB channel and the Alpha channel of the first pixel in the block; For the pixel to be compressed, a difference calculation is performed on the Alpha channel between the actual Alpha value and the predicted value to obtain an Alpha difference value; Perform differential calculation between the actual RGB value and the predicted value in the RGB channel to obtain the RGB differential value; The RGB channel reference value, the Alpha channel reference value, the Alpha difference value, and the RGB difference value are stored in a multi-level partition encoding to compress the block.
2. The data compression method according to claim 1, characterized in that: For the pixel to be compressed, performing a difference calculation between an actual Alpha value and a predicted value in an Alpha channel to obtain an Alpha difference value; The step of performing a difference calculation between the actual RGB value and the predicted value in the RGB channel and obtaining the RGB difference value also includes: The differential calculation of the RGB channels includes a first-order differential calculation and a second-order differential calculation, and the RGB differential value is a second-order differential value.
3. The data compression method according to claim 2, characterized in that: The step of performing multi-level partition encoding and storage of the RGB channel reference value, the Alpha channel reference value, the Alpha difference value, and the RGB difference value to compress the block further includes: The Alpha difference value and its bit width code, and the RGB difference value and its bit width code are partitioned and stored separately.
4. A data decompression method, characterized in that: include: Extracting a multi-level partition code of pixel data in a block including a color buffer, wherein the multi-level partition code includes an alpha difference value and an RGB difference value of pixels in the block; The Alpha difference value and the RGB difference value are restored according to the RGB value and the Alpha value of the adjacent decompressed pixels by using a differential algorithm to obtain the RGB value and the Alpha value of the pixel to be decompressed.
5. The data decompression method according to claim 4, characterized in that: The step of extracting the multi-level partition code of the pixel data in the block including the color buffer, wherein the multi-level partition code includes the alpha difference value and the RGB difference value of the pixels in the block, further comprises: The multi-level partition coding also includes the Alpha differential value bit width coding and the RGB differential value bit width coding of the pixels in the block.
6. The data decompression method according to claim 5, characterized in that: The step of extracting the multi-level partition code of the pixel data in the block including the color buffer, wherein the multi-level partition code includes the alpha difference value and the RGB difference value of the pixels in the block, further comprises: The RGB difference value is a second-order difference value.
7. A data compression system, characterized in that: include: Prediction module, difference module and encoding module; among them, A prediction module is used for predicting the RGB channel and the Alpha channel of the pixel to be compressed in the block of the color buffer using the RGB value and the Alpha value of the adjacent compressed pixel as the predicted value of the pixel to be compressed in the RGB channel and the Alpha channel; and using the preset RGB channel reference value and the Alpha channel reference value as the predicted value of the RGB channel and the Alpha channel of the first pixel in the block; A difference module is used to perform a difference calculation between an actual Alpha value and a predicted value on the Alpha channel of the pixel to be compressed, and obtain an Alpha difference value; and perform a difference calculation between an actual RGB value and a predicted value on the RGB channel, and obtain an RGB difference value; The encoding module is used to perform multi-level partition encoding and storage on the RGB channel reference value, the Alpha channel reference value, the Alpha difference value, and the RGB difference value to compress the block.
8. A data decompression system, characterized in that: include: Extraction module and restoration module; wherein, An extraction module, used for extracting a multi-level partition code of pixel data in a block including a color buffer, wherein the multi-level partition code includes an Alpha difference value and an RGB difference value of pixels in the block; The restoration module is used to restore the Alpha difference value and the RGB difference value according to the RGB value and Alpha value of the adjacent decompressed pixels through a differential algorithm to obtain the RGB value and Alpha value of the pixel to be decompressed.
9. A computer device, characterized in that: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: A computer program is stored thereon; the computer program is executed by a processor to implement the method according to any one of claims 1 to 6.