Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation

TL;DR

This paper introduces a new self-supervised approach for scene flow estimation using adversarial metric learning, along with a benchmark dataset to evaluate models on various complexity levels of 3D scene motion.

Contribution

It proposes a novel adversarial metric learning framework for self-supervised scene flow estimation and provides a comprehensive benchmark dataset for evaluating such models.

Findings

The setup maintains motion coherence and local geometry.

Many self-supervised baselines struggle with occlusions.

Benchmark reveals insights into model performance across complexities.

Abstract

Scene flow is the task of estimating 3D motion vectors to individual points of a dynamic 3D scene. Motion vectors have shown to be beneficial for downstream tasks such as action classification and collision avoidance. However, data collected via LiDAR sensors and stereo cameras are computation and labor intensive to precisely annotate for scene flow. We address this annotation bottleneck on two ends. We propose a 3D scene flow benchmark and a novel self-supervised setup for training flow models. The benchmark consists of datasets designed to study individual aspects of flow estimation in progressive order of complexity, from a single object in motion to real-world scenes. Furthermore, we introduce Adversarial Metric Learning for self-supervised flow estimation. The flow model is fed with sequences of point clouds to perform flow estimation. A second model learns a latent metric to distinguish between the points translated by the flow estimations and the target point cloud. This latent metric is learned via a Multi-Scale Triplet loss, which uses intermediary feature vectors for the loss calculation. We use our proposed benchmark to draw insights about the performance of the baselines and of different models when trained using our setup. We find that our setup is able to keep motion coherence and preserve local geometries, which many self-supervised baselines fail to grasp. Dealing with occlusions, on the other hand, is still an open challenge.