Improved cascade structure multi-view three-dimensional reconstruction method

Abstract

The invention discloses an improved cascade structure multi-view three-dimensional reconstruction method. The method comprises the following steps: carrying out feature extraction on an original image by using a U-shape network structure; introducing CBAM to further process a feature map, extracted by a 2D U-shape feature extraction module, of the topmost layer; inputting the extracted features into a channel attention module, and respectively sending the extracted features into a shared two-layer neural network; summing and merging the output features element by element, obtaining a weight coefficient through a sigmoid activation function, and finally multiplying the weight coefficient by the original features to obtain new features; and the estimation quality of the depth map is improved. Feature extraction is performed by using a U-shape network structure; Feature enhancement is performed on the extracted features by using a CBAM module; in order to increase the correlation between different layers of cost bodies and enable information in the cost bodies to be transmitted layer by layer, a cost body separation fusion device is designed to improve the estimation quality of the depth map.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an improved cascade structure multi-view stereo reconstruction method. Background technique [0002] Multi-view stereo (Multi-view Stereo, MVS) is a reconstruction method that uses a set of images with known camera parameters to restore the 3D model of the scene in the image. Traditional algorithms usually use the projection relationship between multiple views to calculate the corresponding points and restore scene information through formulas. Although these methods achieve good results in ideal Lambertian scenes, they often fail to obtain satisfactory reconstruction results in the case of texture scarcity, texture repetition, or lighting changes. In recent years, deep learning technology has developed rapidly in the field of computer vision, which has stimulated people's interest in improving the reconstruction structure. The derived learning-based multi-v...

AI Technical Summary

Problems solved by technology

However, the existing methods still have room for improvement in the regularization of matching costs and the optimization of depth estimation results, and the efficiency of the algorithm needs to be further improved.

Images