Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision

TL;DR

This paper introduces a Bayesian learning approach for semi-dense active stereo vision that refines disparity maps by jointly learning to improve accuracy and invalidate unreliable pixels, outperforming current methods.

Contribution

It presents a novel neural network training strategy that jointly refines disparity and invalidates pixels using Bayesian modeling, enhancing subpixel accuracy in active stereo vision.

Findings

Outperforms state-of-the-art active stereo models on Active-Passive SimStereo dataset.

Compares favorably with passive stereo models on Middlebury dataset.

Doubles accuracy by learning to refine and invalidate pixels.

Abstract

A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision. Active vision systems enable more accurate estimations of dense disparity compared to passive stereo. However, subpixel-accurate disparity estimation remains an open problem that has received little attention. In this paper, we propose a new learning strategy to train neural networks to estimate high-quality subpixel disparity maps for semi-dense active stereo vision. The key insight is that neural networks can double their accuracy if they are able to jointly learn how to refine the disparity map while invalidating the pixels where there is insufficient information to correct the disparity estimate. Our approach is based on Bayesian modeling where validated and invalidated pixels are defined by their stochastic properties, allowing the model to learn how to choose by itself which pixels are worth its attention. Using active stereo datasets such as Active-Passive SimStereo, we demonstrate that the proposed method outperforms the current state-of-the-art active stereo models. We also demonstrate that the proposed approach compares favorably with state-of-the-art passive stereo models on the Middlebury dataset.