CVJun 29, 2020

Level Set Stereo for Cooperative Grouping with Occlusion

arXiv:2006.16094v31 citations
Originality Incremental advance
AI Analysis

This addresses a specific challenge in stereo vision for computer vision applications, but it is incremental as it builds on existing occlusion-handling methods.

The paper tackled the problem of localizing stereo boundaries in occluded regions by introducing an energy and level-set optimizer that encodes occlusion geometry, resulting in more accurate boundaries than previous techniques on Middlebury and Falling Things datasets.

Localizing stereo boundaries is difficult because matching cues are absent in the occluded regions that are adjacent to them. We introduce an energy and level-set optimizer that improves boundaries by encoding the essential geometry of occlusions: The spatial extent of an occlusion must equal the amplitude of the disparity jump that causes it. In a collection of figure-ground scenes from Middlebury and Falling Things stereo datasets, the model provides more accurate boundaries than previous occlusion-handling techniques.

Code Implementations1 repo
Foundations

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

Your Notes