Full Matching on Low Resolution for Disparity Estimation

TL;DR

This paper introduces a multistage full matching scheme for disparity estimation that improves accuracy by decomposing the task into multiple stages and leveraging their relationships, outperforming existing methods.

Contribution

The work proposes a novel multistage full matching approach with a stages mutual aid strategy, enhancing disparity accuracy by decoupling similarity scores from low-resolution volumes.

Findings

Achieves more accurate disparity estimation on benchmark datasets.

Outperforms state-of-the-art methods on Scene Flow, KITTI 2012, and KITTI 2015.

Demonstrates the effectiveness of multistage decomposition and mutual aid strategy.

Abstract

A Multistage Full Matching disparity estimation scheme (MFM) is proposed in this work. We demonstrate that decouple all similarity scores directly from the low-resolution 4D volume step by step instead of estimating low-resolution 3D cost volume through focusing on optimizing the low-resolution 4D volume iteratively leads to more accurate disparity. To this end, we first propose to decompose the full matching task into multiple stages of the cost aggregation module. Specifically, we decompose the high-resolution predicted results into multiple groups, and every stage of the newly designed cost aggregation module learns only to estimate the results for a group of points. This alleviates the problem of feature internal competitive when learning similarity scores of all candidates from one low-resolution 4D volume output from one stage. Then, we propose the strategy of \emph{Stages Mutual Aid}, which takes advantage of the relationship of multiple stages to boost similarity scores estimation of each stage, to solve the unbalanced prediction of multiple stages caused by serial multistage framework. Experiment results demonstrate that the proposed method achieves more accurate disparity estimation results and outperforms state-of-the-art methods on Scene Flow, KITTI 2012 and KITTI 2015 datasets.