Welsch Based Multiview Disparity Estimation
James L. Gray, Aous T. Naman, David S. Taubman

TL;DR
This paper introduces a novel disparity estimation method using a Welsch loss function within a variational framework, effectively handling occlusions and improving robustness in multiview scenarios.
Contribution
It proposes a Welsch loss-based variational approach with a disciplined warping and progressive view inclusion strategy for better multiview disparity estimation.
Findings
Outperforms conventional variational methods in robustness and accuracy
Effectively handles occlusions in high-view disparity estimation
Reduces the need for coarse-to-fine strategies
Abstract
In this work, we explore disparity estimation from a high number of views. We experimentally identify occlusions as a key challenge for disparity estimation for applications with high numbers of views. In particular, occlusions can actually result in a degradation in accuracy as more views are added to a dataset. We propose the use of a Welsch loss function for the data term in a global variational framework for disparity estimation. We also propose a disciplined warping strategy and a progressive inclusion of views strategy that can reduce the need for coarse to fine strategies that discard high spatial frequency components from the early iterations. Experimental results demonstrate that the proposed approach produces superior and/or more robust estimates than other conventional variational approaches.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
