SegviGen: Repurposing 3D Generative Model for Part Segmentation

TL;DR

SegviGen is a novel framework that leverages pretrained 3D generative models for efficient 3D part segmentation, achieving significant improvements with minimal labeled data.

Contribution

It introduces a new method that repurposes 3D generative priors for part segmentation, reducing data requirements and enhancing performance.

Findings

Improves interactive segmentation accuracy by 40%.

Enhances full segmentation accuracy by 15%.

Operates effectively with only 0.32% of labeled data.

Abstract

We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes a 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the labeled training data. It demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. See our project page at https://fenghora.github.io/SegviGen-Page/.