IVCVOct 2, 2021

Welsch Based Multiview Disparity Estimation

arXiv:2110.00803v14 citations
Originality Incremental advance
AI Analysis

This work addresses disparity estimation for multiview applications, but it is incremental as it builds on existing variational frameworks with specific improvements.

The paper tackled the problem of disparity estimation from many views, identifying occlusions as a key challenge that can degrade accuracy with more views, and proposed using a Welsch loss function, disciplined warping, and progressive view inclusion to achieve superior and more robust estimates compared to conventional variational approaches.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes