G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping
This addresses a new problem in 3D shape analysis for applications like assembly or reconstruction, but it appears incremental as it adapts existing techniques like GNNs to a specific task.
The paper tackles the novel task of 3D part grouping, which involves finding all possible combinations of scattered parts from various shapes, and proposes the G-FARS framework that uses a gradient-field-based selection GNN to autonomously group parts, achieving results as described in the abstract.
This paper proposes a novel task named "3D part grouping". Suppose there is a mixed set containing scattered parts from various shapes. This task requires algorithms to find out every possible combination among all the parts. To address this challenge, we propose the so called Gradient Field-based Auto-Regressive Sampling framework (G-FARS) tailored specifically for the 3D part grouping task. In our framework, we design a gradient-field-based selection graph neural network (GNN) to learn the gradients of a log conditional probability density in terms of part selection, where the condition is the given mixed part set. This innovative approach, implemented through the gradient-field-based selection GNN, effectively captures complex relationships among all the parts in the input. Upon completion of the training process, our framework becomes capable of autonomously grouping 3D parts by iteratively selecting them from the mixed part set, leveraging the knowledge acquired by the trained gradient-field-based selection GNN. Our code is available at: https://github.com/J-F-Cheng/G-FARS-3DPartGrouping.