通过投票机制让点云运动保持局部刚性，提升自监督场景流精度。
VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow
- 设计可微投票空间，自动识别邻近点共享的运动方向。
- 在Argoverse 2和Waymo上优于基线模型，计算开销极小。
- 适配主流网络结构，适合自动驾驶点云运动估计任务。
场景流估计旨在从相邻两帧激光雷达扫描中恢复每个点的运动。然而，在真实场景如自动驾驶中，点通常并非独立运动，尤其同一物体上的邻近点常具有相同运动。现有方法多通过后处理或附加正则化来引入局部刚性约束，但缺乏模型结构中的归纳偏置，导致学习效率低、性能受限。本文提出轻量级投票模块，将局部刚性作为神经网络的内在结构先验，实现端到端学习。该模块构建离散投票空间以覆盖所有可能位移，并通过可微投票机制找出邻近点共享的最佳运动。为保证效率，模块在柱状体（pillar）层面操作，学习每柱的代表性特征用于投票。将该模块嵌入主流模型，在Argoverse 2与Waymo数据集上均取得更好效果，仅增加微小计算开销。代码已开源。
原文摘要 · Abstract (English)
Scene flow estimation aims to recover per-point motion from two adjacent LiDAR scans. However, in real-world applications such as autonomous driving, points rarely move independently of others, especially for nearby points belonging to the same object, which often share the same motion. Incorporating this locally rigid motion constraint has been a key challenge in self-supervised scene flow estimation, which is often addressed by post-processing or appending extra regularization. While these approaches are able to improve the rigidity of predicted flows, they lack an architectural inductive bias for local rigidity within the model structure, leading to suboptimal learning efficiency and inferior performance. In contrast, we enforce local rigidity with a lightweight add-on module in neural network design, enabling end-to-end learning. We design a discretized voting space that accommodates all possible translations and then identify the one shared by nearby points by differentiable voting. Additionally, to ensure computational efficiency, we operate on pillars rather than points and learn representative features for voting per pillar. We plug the Voting Module into popular model designs and evaluate its benefit on Argoverse 2 and Waymo datasets. We outperform baseline works with only marginal compute overhead. Code is available at https://github.com/tudelft-iv/VoteFlow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。