CVAIMay 10, 2021

SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation

arXiv:2105.04447v450 citations
AI Analysis

This addresses the problem of accurately estimating 3D motions from unstructured point clouds for applications like autonomous driving and robotics, representing a strong specific gain rather than an incremental improvement.

The paper tackles scene flow estimation from point clouds by proposing the Sparse Convolution-Transformer Network (SCTN), which achieves state-of-the-art results with errors of 0.038 and 0.037 EPE3D on FlyingThings3D and KITTI datasets, significantly outperforming previous methods.

We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds. Estimating 3D motions for point clouds is challenging, since a point cloud is unordered and its density is significantly non-uniform. Such unstructured data poses difficulties in matching corresponding points between point clouds, leading to inaccurate flow estimation. We propose a novel architecture named Sparse Convolution-Transformer Network (SCTN) that equips the sparse convolution with the transformer. Specifically, by leveraging the sparse convolution, SCTN transfers irregular point cloud into locally consistent flow features for estimating continuous and consistent motions within an object/local object part. We further propose to explicitly learn point relations using a point transformer module, different from exiting methods. We show that the learned relation-based contextual information is rich and helpful for matching corresponding points, benefiting scene flow estimation. In addition, a novel loss function is proposed to adaptively encourage flow consistency according to feature similarity. Extensive experiments demonstrate that our proposed approach achieves a new state of the art in scene flow estimation. Our approach achieves an error of 0.038 and 0.037 (EPE3D) on FlyingThings3D and KITTI Scene Flow respectively, which significantly outperforms previous methods by large margins.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes