无需标注数据，用扩散模型学3D关键点，能还原形状且结构可插值。
KeyPointDiffuser: Unsupervised 3D Keypoint Learning via Latent Diffusion Models
- 用潜在扩散模型从点云无监督学习3D关键点
- 关键点跨物体具重复空间结构，插值平滑，几何变化可捕捉
- 在多类别上表现强，关键点一致性提升6个百分点
在计算机视觉与图形学中，无监督地理解和表示3D物体的结构仍是核心挑战。现有大多数无监督关键点方法不适用于无条件生成场景，限制了其在现代3D生成流水线中的应用；我们的方法明确填补这一空白。提出一种从点云数据中无监督学习空间结构化3D关键点的框架。这些关键点作为紧凑且可解释的表示，用于引导解构扩散模型（EDM）重建完整形状。学习到的关键点在不同物体实例间展现出可重复的空间结构，并支持关键点空间中的平滑插值，表明其捕捉到了几何变化。在多种物体类别上表现优异，关键点一致性相比以往方法提升6个百分点。
原文摘要 · Abstract (English)
Understanding and representing the structure of 3D objects in an unsupervised manner remains a core challenge in computer vision and graphics. Most existing unsupervised keypoint methods are not designed for unconditional generative settings, restricting their use in modern 3D generative pipelines; our formulation explicitly bridges this gap. We present an unsupervised framework for learning spatially structured 3D keypoints from point cloud data. These keypoints serve as a compact and interpretable representation that conditions an Elucidated Diffusion Model (EDM) to reconstruct the full shape. The learned keypoints exhibit repeatable spatial structure across object instances and support smooth interpolation in keypoint space, indicating that they capture geometric variation. Our method achieves strong performance across diverse object categories, yielding a 6 percentage-point improvement in keypoint consistency compared to prior approaches.
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。