A New Approach To Two-View Motion Segmentation Using Global Dimension Minimization

TL;DR

This paper introduces a novel method for two-view motion segmentation using global dimension minimization, leveraging a nonlinear embedding and a new clustering approach to improve accuracy and outlier robustness.

Contribution

It proposes the concept of global dimension minimization for clustering subspaces in two-view motion segmentation, with a fast algorithm and outlier detection framework.

Findings

Achieves state-of-the-art results on outlier-free data

Robustly segments motions in outlier-corrupted data

Introduces a fast projected gradient algorithm for global dimension minimization

Abstract

We present a new approach to rigid-body motion segmentation from two views. We use a previously developed nonlinear embedding of two-view point correspondences into a 9-dimensional space and identify the different motions by segmenting lower-dimensional subspaces. In order to overcome nonuniform distributions along the subspaces, whose dimensions are unknown, we suggest the novel concept of global dimension and its minimization for clustering subspaces with some theoretical motivation. We propose a fast projected gradient algorithm for minimizing global dimension and thus segmenting motions from 2-views. We develop an outlier detection framework around the proposed method, and we present state-of-the-art results on outlier-free and outlier-corrupted two-view data for segmenting motion.