EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support

TL;DR

EgoFlowNet is a weakly-supervised point-level scene flow estimation network that avoids object-based clustering, effectively handling ego-motion and scene flow from LiDAR point clouds in complex scenes.

Contribution

It introduces a novel approach that predicts a binary segmentation mask to guide parallel ego-motion and scene flow branches without relying on object clustering.

Findings

Outperforms state-of-the-art methods on KITTI scenes

Handles ground surface points effectively

Does not require explicit object rigidity assumptions

Abstract

Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable to clustering robustness. In this paper, we propose our EgoFlowNet - a point-level scene flow estimation network trained in a weakly-supervised manner and without object-based abstraction. Our approach predicts a binary segmentation mask that implicitly drives two parallel branches for ego-motion and scene flow. Unlike previous methods, we provide both branches with all input points and carefully integrate the binary mask into the feature extraction and losses. We also use a shared cost volume with local refinement that is updated at multiple scales without explicit clustering or rigidity assumptions. On realistic KITTI scenes, we show that our EgoFlowNet performs better than state-of-the-art methods in the presence of ground surface points.