REVNET: Rotation-Equivariant Point Cloud Completion via Vector Neuron Anchor Transformer

TL;DR

REVNET introduces a rotation-equivariant point cloud completion framework that maintains robustness under arbitrary orientations, outperforming existing methods especially in real-world scenarios.

Contribution

It proposes a novel rotation-equivariant transformer based on Vector Neuron networks, enabling stable point cloud completion without pose alignment.

Findings

Outperforms state-of-the-art on synthetic MVP dataset in equivariant setting.

Delivers competitive results on real-world KITTI dataset without pose alignment.

Utilizes equivariant anchors and a VN Missing Anchor Transformer for local detail preservation.

Abstract

Incomplete point clouds captured by 3D sensors often result in the loss of both geometric and semantic information. Most existing point cloud completion methods are built on rotation-variant frameworks trained with data in canonical poses, limiting their applicability in real-world scenarios. While data augmentation with random rotations can partially mitigate this issue, it significantly increases the learning burden and still fails to guarantee robust performance under arbitrary poses. To address this challenge, we propose the Rotation-Equivariant Anchor Transformer (REVNET), a novel framework built upon the Vector Neuron (VN) network for robust point cloud completion under arbitrary rotations. To preserve local details, we represent partial point clouds as sets of equivariant anchors and design a VN Missing Anchor Transformer to predict the positions and features of missing anchors. Furthermore, we extend VN networks with a rotation-equivariant bias formulation and a ZCA-based layer normalization to improve feature expressiveness. Leveraging the flexible conversion between equivariant and invariant VN features, our model can generate point coordinates with greater stability. Experimental results show that our method outperforms state-of-the-art approaches on the synthetic MVP dataset in the equivariant setting. On the real-world KITTI dataset, REVNET delivers competitive results compared to non-equivariant networks, without requiring input pose alignment. The source code will be released on GitHub under URL: https://github.com/nizhf/REVNET.