Saved in:
Bibliographic Details
Main Authors: Li, Lin, Feng, Haoran, Huang, Zehuan, Chen, Haohua, Nie, Wenbo, Hou, Shaohua, Fan, Keqing, Hu, Pan, Wang, Sheng, Li, Buyu, Sheng, Lu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.16869
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910206867275776
author Li, Lin
Feng, Haoran
Huang, Zehuan
Chen, Haohua
Nie, Wenbo
Hou, Shaohua
Fan, Keqing
Hu, Pan
Wang, Sheng
Li, Buyu
Sheng, Lu
author_facet Li, Lin
Feng, Haoran
Huang, Zehuan
Chen, Haohua
Nie, Wenbo
Hou, Shaohua
Fan, Keqing
Hu, Pan
Wang, Sheng
Li, Buyu
Sheng, Lu
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16869
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SegviGen: Repurposing 3D Generative Model for Part Segmentation
Li, Lin
Feng, Haoran
Huang, Zehuan
Chen, Haohua
Nie, Wenbo
Hou, Shaohua
Fan, Keqing
Hu, Pan
Wang, Sheng
Li, Buyu
Sheng, Lu
Computer Vision and Pattern Recognition
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/.
title SegviGen: Repurposing 3D Generative Model for Part Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.16869