Null-Space Diffusion Sampling for Zero-Shot Point Cloud Completion

Point cloud completion aims at estimating the complete data of objects from degraded observations. Despite existing completion methods achieving impressive performances, they rely heavily on degraded-complete data pairs for supervision. In this work, we propose a novel framework named Null-Space Diffusion Sampling (NSDS) to solve the point cloud completion task in a zero-shot manner. By leveraging a pre-trained point cloud diffusion model as the off-the-shelf generator, our sampling approach can generate desired completion outputs with the guidance of the observed degraded data without any extra training. Furthermore, we propose a tolerant loop mechanism to improve the quality of completion results for hard cases. Experimental results demonstrate our zero-shot framework achieves superior completion performance than unsupervised methods and comparable performance to supervised methods in various degraded situations.

Authors

• Xinhua Cheng School of Electronic and Computer Engineering, Peking University, China Peng Cheng Laboratory, China
• Nan Zhang
• Jiwen Yu Peking University Shenzhen Graduate School
• Yinhuai Wang Peking University Shenzhen Graduate School
• Ge Li Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University
• Jian Zhang

Keywords

• Computer Vision: CV: 3D computer vision