SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation

TL;DR

SegGraph introduces a graph-based approach leveraging SAM segmentation masks to improve few-shot 3D part segmentation by explicitly modeling geometric relationships and ensuring semantic consistency.

Contribution

The paper proposes a novel segment graph propagation method that effectively integrates 2D foundation model features with 3D geometric structures for enhanced segmentation.

Findings

Outperforms baselines by at least 6.9% mIoU on PartNet-E

Achieves strong performance on small components and boundaries

Effectively models geometric relationships via a segment graph

Abstract

This work presents a novel framework for few-shot 3D part segmentation. Recent advances have demonstrated the significant potential of 2D foundation models for low-shot 3D part segmentation. However, it is still an open problem that how to effectively aggregate 2D knowledge from foundation models to 3D. Existing methods either ignore geometric structures for 3D feature learning or neglects the high-quality grouping clues from SAM, leading to under-segmentation and inconsistent part labels. We devise a novel SAM segment graph-based propagation method, named SegGraph, to explicitly learn geometric features encoded within SAM's segmentation masks. Our method encodes geometric features by modeling mutual overlap and adjacency between segments while preserving intra-segment semantic consistency. We construct a segment graph, conceptually similar to an atlas, where nodes represent segments and edges capture their spatial relationships (overlap/adjacency). Each node adaptively modulates 2D foundation model features, which are then propagated via a graph neural network to learn global geometric structures. To enforce intra-segment semantic consistency, we map segment features to 3D points with a novel view-direction-weighted fusion attenuating contributions from low-quality segments. Extensive experiments on PartNet-E demonstrate that our method outperforms all competing baselines by at least 6.9 percent mIoU. Further analysis reveals that SegGraph achieves particularly strong performance on small components and part boundaries, demonstrating its superior geometric understanding. The code is available at: https://github.com/YueyangHu2000/SegGraph.