Year: 2020
Category:
Publication

Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion

Teaser Image of Scene Flow Estimation Publication

Overview

This is a work which we submitted for 3DV 2020 and which was accepted as an oral. In this work, we propose an end-to-end scene flow learning method which jointly estimates the non-rigid residual flow and the ego-motion flow.

Abstract

Most of the current scene flow methods choose to model scene flow as a per point translation vector without differentiating between static and dynamic components of 3D motion. In this work we present an alternative method for end-to-end scene flow learning by joint estimation of non-rigid residual flow and ego-motion flow for dynamic 3D scenes. We propose to learn the relative rigid transformation from a pair of point clouds followed by an iterative refinement. We then learn the non-rigid flow from transformed inputs with the deducted rigid part of the flow. Furthermore, we extend the supervised framework with self-supervisory signals based on the temporal consistency property of a point cloud sequence. Our solution allows both training in a supervised mode complemented by self-supervisory loss terms as well as training in a fully self-supervised mode. We demonstrate that decomposition of scene flow into non-rigid flow and ego-motion flow along with an introduction of the self-supervisory signals allowed us to outperform the current state-of-the-art supervised methods.

Authors

Ivan Tishchenko, Sandro Lombardi, Martin R. Oswald and Marc Pollefeys

Venue

3DV 2020, Online

Links