Depth completion method for sparse depth map, computer device and storage medium

Abstract

The invention discloses a depth completion method for a sparse depth map, a computer device and a storage medium, and the process of training a neural network in the depth completion method comprises the steps: obtaining a color image and a depth map truth value, carrying out the equal-distance sampling of the depth map truth value, and obtaining a sparse depth map. The method comprises the following steps: extracting a color image and a sparse depth map to obtain a multi-scale feature map, carrying out regression on the multi-scale feature map to obtain an initial depth map, calculating pixel correlation, carrying out multi-time iterative filtering on the initial depth map to obtain a dense depth map, and carrying out multi-round iterative processing on the dense depth map to train an image consistency optimization module. According to the method, the neural network is trained, the prediction effect of the image consistency optimization module on the pixel depth at the boundary of the dense depth map can be improved, so that the image consistency optimization module has the capability of predicting the pixel depth according to the dense depth map, and the neural network has the capability of depth completion. The method is widely applied to the technical field of image processing.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a depth completion method for a sparse depth map, a computer device and a storage medium. Background technique [0002] Depth perception is the basic task of 3D vision. Through depth perception, the distance between the point on the object represented by each pixel in the image and a certain reference plane can be obtained, which provides important applications for automatic driving control, robotics, augmented reality, etc. control parameters. Depth perception technology has achieved rapid development in recent years, but how to obtain high-precision, high-resolution depth maps at low cost is still a challenging task. Low-cost, low-power depth sensors usually can only obtain low-resolution, very sparse depth maps, lacking depth information of a large number of pixels, while practical applications require dense depth maps. [0003] Terminology Explanation: [...

AI Technical Summary

Problems solved by technology

[0007] Aiming at at least one technical problem such as the sparse depth map obtained in the current depth perception technology cannot meet the requirements for dense depth ma

Images