用扩散模型生成多姿态猜测，提升点云6D位姿估计的准确性。
Particle-based 6D Object Pose Estimation from Point Clouds using Diffusion Models
- 基于扩散模型生成多个位姿候选，解决遮挡对称性带来的歧义。
- 在Linemod数据集上达到竞争性精度，推理速度更快。
- 仅使用点云输入，适配点云处理新进展，适合3D视觉研究者。
单视角下的物体位姿估计仍具挑战性，尤其受部分可观测性、遮挡和物体对称性影响，导致位姿歧义。本文提出一种基于扩散模型的生成式6D位姿估计方法，在推理阶段可采样多个位姿假设（粒子）。为将这些信息提炼为单一估计，提出两种无需额外训练或高计算开销的新颖选择策略。与多数依赖图像域且仅用深度信息做精修的方法不同，本模型完全基于点云数据运行，利用最近的点云处理进展，在SE(3)等变潜在空间中操作，支撑粒子选择策略并提升推理效率。大量实验表明，该方法在Linemod数据集上表现优异，验证了设计的有效性。代码已开源：https://github.com/zitronian/6DPoseDiffusion。
原文摘要 · Abstract (English)
Object pose estimation from a single view remains a challenging problem. In particular, partial observability, occlusions, and object symmetries eventually result in pose ambiguity. To account for this multimodality, this work proposes training a diffusion-based generative model for 6D object pose estimation. During inference, the trained generative model allows for sampling multiple particles, i.e., pose hypotheses. To distill this information into a single pose estimate, we propose two novel and effective pose selection strategies that do not require any additional training or computationally intensive operations. Moreover, while many existing methods for pose estimation primarily focus on the image domain and only incorporate depth information for final pose refinement, our model solely operates on point cloud data. The model thereby leverages recent advancements in point cloud processing and operates upon an SE(3)-equivariant latent space that forms the basis for the particle selection strategies and allows for improved inference times. Our thorough experimental results demonstrate the competitive performance of our approach on the Linemod dataset and showcase the effectiveness of our design choices. Code is available at https://github.com/zitronian/6DPoseDiffusion .
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。