A Flexible Recursive Network for Video Stereo Matching Based on Residual Estimation

TL;DR

This paper introduces RecSM, a recursive neural network for video stereo matching that leverages residual estimation and multi-scale modules to significantly speed up processing while maintaining high accuracy.

Contribution

The paper proposes RecSM, a novel residual estimation network with a flexible recursive structure and modules for efficient and accurate video stereo matching.

Findings

RecSM achieves 4x speed improvement over ACVNet.

RecSM maintains high accuracy with only 0.7% decrease.

The flexible SCS design adapts to different practical scenarios.

Abstract

Due to the high similarity of disparity between consecutive frames in video sequences, the area where disparity changes is defined as the residual map, which can be calculated. Based on this, we propose RecSM, a network based on residual estimation with a flexible recursive structure for video stereo matching. The RecSM network accelerates stereo matching using a Multi-scale Residual Estimation Module (MREM), which employs the temporal context as a reference and rapidly calculates the disparity for the current frame by computing only the residual values between the current and previous frames. To further reduce the error of estimated disparities, we use the Disparity Optimization Module (DOM) and Temporal Attention Module (TAM) to enforce constraints between each module, and together with MREM, form a flexible Stackable Computation Structure (SCS), which allows for the design of different numbers of SCS based on practical scenarios. Experimental results demonstrate that with a stack count of 3, RecSM achieves a 4x speed improvement compared to ACVNet, running at 0.054 seconds based on one NVIDIA RTX 2080TI GPU, with an accuracy decrease of only 0.7%. Code is available at https://github.com/Y0uchenZ/RecSM.