Three-dimensional image color correction method and system based on matching and fusion

Abstract

The invention relates to a stereo image color correction method and system based on matching and fusion. The method comprises the following steps: S1, establishing a training set comprising undistorted stereo images and distorted stereo images; S2, constructing a color correction initial model based on parallax attention and a loss function thereof, training to obtain a trained color correction initial model, and performing initial color correction on the target image by using the trained color correction initial model to obtain an initial correction image; S3, calculating an optical flow from the initial correction image to the reference image by using an optical flow network, and performing image deformation and hole filling on the reference image to obtain a matched target image; S4, constructing an image fusion network model based on a U-net model architecture and a loss function of the image fusion network model, and training to obtain a trained image fusion network model; and S5, performing color correction on the distorted stereo image to be corrected by using the models trained in the steps S2 to S4. The method and the system are beneficial to quickly and efficiently correcting the color difference between the left view and the right view of the stereo image.

Description

technical field [0001] The invention relates to the fields of image processing and computer vision, in particular to a method and system for color correction of stereoscopic images based on matching and fusion. Background technique [0002] With the rapid development of computer vision and the continuous advancement of multimedia technology, binocular stereo vision has attracted widespread attention and developed rapidly for its immersive visual effects. Compared with the flatness of traditional two-dimensional images, binocular stereo vision brings people a more real, natural and shocking experience. In some specific researches, such as stereoscopic image color correction, multi-viewpoint video color correction, panoramic image stitching, remote sensing image fusion, etc., people hope that the obtained image groups have better color consistency. However, due to the influence of different factors such as camera parameter settings and placement, light source distribution cha...

AI Technical Summary

Problems solved by technology

These methods can get better local color correction results, but it takes too long, and the image fusion strategy used will lead to structural deformation in some results

Images