Bibliographic Details
Title: |
Consensus Learning with Deep Sets for Essential Matrix Estimation |
Authors: |
Moran, Dror, Margalit, Yuval, Trostianetsky, Guy, Khatib, Fadi, Galun, Meirav, Basri, Ronen |
Publication Year: |
2024 |
Collection: |
Computer Science |
Subject Terms: |
Computer Science - Computer Vision and Pattern Recognition |
More Details: |
Robust estimation of the essential matrix, which encodes the relative position and orientation of two cameras, is a fundamental step in structure from motion pipelines. Recent deep-based methods achieved accurate estimation by using complex network architectures that involve graphs, attention layers, and hard pruning steps. Here, we propose a simpler network architecture based on Deep Sets. Given a collection of point matches extracted from two images, our method identifies outlier point matches and models the displacement noise in inlier matches. A weighted DLT module uses these predictions to regress the essential matrix. Our network achieves accurate recovery that is superior to existing networks with significantly more complex architectures. |
Document Type: |
Working Paper |
Access URL: |
http://arxiv.org/abs/2406.17414 |
Accession Number: |
edsarx.2406.17414 |
Database: |
arXiv |