外观
论文arXiv 2610.1289519 天前
MeshBind：用于非刚性场景流自动标注的点到网格绑定
原文链接：MeshBind: Point-to-Mesh Binding for Non-Rigid Scene Flow Automatic Annotation（arXiv 2610.12895 · 发布日期：2026-10-09）
MeshBind: Point-to-Mesh Binding for Non-Rigid Scene Flow Automatic Annotation
MeshBind用多视角网格重建与点到网格绑定自动标注非刚性目标场景流，并在SFB基准上验证效果。
核心要点
- 自动驾驶和机器人需要场景流，但行人等非刚性目标真值很难获取。
- 方法从六个环视相机重建关节网格并配准到LiDAR坐标系。
- 局部坐标系绑定使点随网格三角面运动，适应关节形变并保持刚体不变性。
- 在SF-Studio中实现并发布SFB，微调后三类EPE降低2-3倍。
验证范围与局限：验证范围为基于公开SUScape构建的SFB基准，覆盖41k帧行人非刚性逐点标注。
英文摘要 (Abstract)
Scene flow estimation is essential for many autonomous driving (AD) and robotic applications, but obtaining ground-truth scene flow for non-rigid objects such as pedestrians is highly difficult. We present MeshBind, an automatic annotation method that uses mesh models to generate per-point scene flow for non-rigid objects. The novelty of this work is threefold: 1) developing a multi-view module that reconstructs an articulated mesh model from six surround cameras and registers it to the LiDAR frame; 2) developing a local-frame binding technique that attaches each point to the mesh via a per-triangle tangent-normal frame, invariant under rigid motion yet adaptive to articulated deformation; 3) developing a three-layer flow registration pipeline that combines ego-vehicle motion compensation, box binding, and mesh binding to produce full-scene per-point flow. We implement MeshBind in SF-Studio, an interactive annotation tool that visualises flow and allows human mesh corrections with automatic recomputation. We also release SFB (SUScape-Flow Benchmark), a large-scale benchmark built on the public SUScape dataset, covering 41k frames with per-point non-rigid pedestrian annotations and a Rigid/Semi-Rigid/Non-Rigid evaluation protocol. Experiments show that fine-tuning on SFB reduces three-way endpoint error (EPE) by 2-3x, and brings non-rigid EPE to the same level as rigid EPE.
作者：Yinqi Chen, E Li, ShuaiJun Wang, Weiyuan Peng, Zhang, Meiying, Qi Hao
来源
本页事实对应的公开页面，以原文为准。