Score-PA: Score-based 3D Part Assembly
This addresses the challenge of assembling 3D parts without predefined instructions, relevant to robotics and computer vision, with incremental improvements in speed.
The paper tackles autonomous 3D part assembly by formulating it as a generative task and introduces Score-PA, a score-based framework that uses a Fast Predictor-Corrector Sampler to accelerate inference, outperforming state-of-the-art methods in quality and diversity.
Autonomous 3D part assembly is a challenging task in the areas of robotics and 3D computer vision. This task aims to assemble individual components into a complete shape without relying on predefined instructions. In this paper, we formulate this task from a novel generative perspective, introducing the Score-based 3D Part Assembly framework (Score-PA) for 3D part assembly. Knowing that score-based methods are typically time-consuming during the inference stage. To address this issue, we introduce a novel algorithm called the Fast Predictor-Corrector Sampler (FPC) that accelerates the sampling process within the framework. We employ various metrics to assess assembly quality and diversity, and our evaluation results demonstrate that our algorithm outperforms existing state-of-the-art approaches. We release our code at https://github.com/J-F-Cheng/Score-PA_Score-based-3D-Part-Assembly.