Convolutional filtering optimizing method based on linear texture filtering

Abstract

The invention discloses a convolutional filtering optimizing method based on linear texture filtering. The method comprises the following steps of: dividing a convolutional filter into two one-dimensional filters if the convolutional filter can be separated; inspecting the weights in a convolution kernel and pairing two adjacent weights of which the values are not zero and the sizes are same so as to ensure that paired weights in the whole convolution kernel are as many as possible; calculating the paired weights to acquire coordinate offset amount required by the linear texture filtering and a new weight; performing texture searching according to the coordinate offset amount in a mode of linear texture filtering; multiplying the acquired texture value by the corresponding new weight to acquire an action result of the paired weight in the convolutional filtering; performing normal convolutional filtering on the weights which are not paired; and adding the filtering results with the results of the paired weight to acquire the whole convolutional filtering result. By the convolutional filtering optimizing method, a linear texture filtering function of a modern ground power unit (GPU) is utilized, and the times for performing texture searching, multiplication and addition which are required for convolutional filtering in the real-time image rendering process are reduced, so that the aim of improving the convolutional filtering efficiency is fulfilled.

Description

technical field [0001] The invention belongs to the field of computer graphics, and relates to how to use the linear texture filtering function of graphics hardware to reduce the number of texture search, multiplication and addition required when performing convolution filtering in real-time image rendering, so as to improve the efficiency of convolution filtering the goal of. Background technique [0002] Texture mapping is one of the most commonly used techniques in graphics rendering. In the process of texture mapping, texture search is an essential step. Texture search is to find the value of the corresponding texel (corresponding to the pixel in the image) in the texture according to the given texture coordinates for subsequent mapping. In most cases, the texture coordinates used in the texture search are not integers, that is, the coordinates correspond to not a specific texel in the texture but a certain position in some adjacent texels, and such a texture search is ...

AI Technical Summary

Problems solved by technology

"Nearest filtering" is the simplest and fastest method, it directly takes the value of the texel closest to the texture coordinate as the result of texture lookup, but the effect is not very good

Images