Zero-shot Point Cloud Completion Via 2D Priors
arxiv(2024)
摘要
3D point cloud completion is designed to recover complete shapes from
partially observed point clouds. Conventional completion methods typically
depend on extensive point cloud data for training
often constrained to object categories similar to those seen during training.
In contrast, we propose a zero-shot framework aimed at completing partially
observed point clouds across any unseen categories. Leveraging point rendering
via Gaussian Splatting, we develop techniques of Point Cloud Colorization and
Zero-shot Fractal Completion that utilize 2D priors from pre-trained diffusion
models to infer missing regions. Experimental results on both synthetic and
real-world scanned point clouds demonstrate that our approach outperforms
existing methods in completing a variety of objects without any requirement for
specific training data.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要