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

TL;DR

This paper introduces a novel end-to-end method for scene flow estimation that decomposes motion into non-rigid residual flow and ego-motion, utilizing self-supervision to outperform existing methods.

Contribution

It presents a joint estimation framework for non-rigid residual flow and ego-motion, incorporating self-supervisory signals for improved scene flow learning.

Findings

Outperforms current state-of-the-art supervised methods

Supports both supervised and self-supervised training modes

Effectively decomposes scene flow into rigid and non-rigid components

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.