CVITApr 7, 2018

Estimation of Camera Locations in Highly Corrupted Scenarios: All About that Base, No Shape Trouble

arXiv:1804.02591v115 citations
Originality Incremental advance
AI Analysis

This work addresses a specific challenge in computer vision for 3D reconstruction, but it is incremental as it builds on existing solvers with a preprocessing step.

The paper tackles the problem of camera location estimation in structure from motion under highly corrupted pairwise directions by identifying and removing corrupted data using a geometric consistency condition, resulting in significant improvement in performance as demonstrated by numerical results on artificial and real data.

We propose a strategy for improving camera location estimation in structure from motion. Our setting assumes highly corrupted pairwise directions (i.e., normalized relative location vectors), so there is a clear room for improving current state-of-the-art solutions for this problem. Our strategy identifies severely corrupted pairwise directions by using a geometric consistency condition. It then selects a cleaner set of pairwise directions as a preprocessing step for common solvers. We theoretically guarantee the successful performance of a basic version of our strategy under a synthetic corruption model. Numerical results on artificial and real data demonstrate the significant improvement obtained by our strategy.

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