GPU compressed texture processing method

Abstract

The invention discloses a GPU compressed texture processing method. The method specifically comprises the following steps: further coding GPU compressed texture resources; employing a similar vector quantization method for processing a data block; recalculating the pixel palette index by controlling the mean square error; employing a differential coding thought as reference, removing spatial redundancy, generating a pixel palette index dictionary, performing YCoCg transformation and discrete wavelet compression on pixels in all the data blocks, further removing the data redundancy, and finallyprocessing and interweaving data streams based on a finite state entropy coding method of an asymmetric digital system to generate efficient compressed texture resources. The invention has the beneficial effects that the storage size of compressed texture resources is reduced; the data redundancy is reduced, and the decoding performance and the loading efficiency are improved; the occupation of avideo memory is reduced, the loading speed of material resources is increased, and the CPU load is reduced; the storage and network transmission cost is reduced, the loading and decoding speed of material resources is improved, and the contradiction between the storage space and the decoding efficiency is solved.

Description

technical field [0001] The present invention relates to the technical field related to graphics processing, in particular to a GPU compressed texture processing method. Background technique [0002] In computer graphics, texture usually refers to the image resource applied to the surface material of the object or drawn on the screen. The texture map maps the image resource to the surface of the object in a specific way to enhance the realism and visual effect of the object. It is one of the basic technologies of computer graphics and is widely used in the field of graphics rendering. [0003] Because traditional image compression formats (JPG / PNG / WebP) have high compression ratio and compression quality, texture material resources are mostly used for file storage and network transmission. Although the storage and transmission costs required by the traditional image compression format are low, due to the high computational complexity of the decoding algorithm, it cannot meet...

AI Technical Summary

Problems solved by technology

GPU compressed texture formats (DXT / PVRTC / ETC / ASTC, etc.) use fixed bit rate compression algorithms to process texture images to reduce the complexity of hardware decoding algorithms and meet texture random access requirements, but the cost of file storage and network transmission is high

Images