Consensus Learning with Deep Sets for Essential Matrix Estimation

Dror Moran, Yuval Margalit, Guy Trostianetsky, Fadi Khatib, Meirav Galun, Ronen Basri

Keywords: Computer Vision, Consensus learning, Relative pose estimation, Deep Sets

Abstract: 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.

Primary Area: Machine vision

Submission Number: 15909