PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation

2026-09-22

AI Summary

本文提出PartLLM，一种统一的多模态模型，通过意图条件生成方法解决3D部件分割问题，支持文本引导、交互式及全形状语义分解。

Abstract

Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies, but existing approaches typically only address a specific setting, such as text-guided part segmentation or point-based interaction. In this work, we argue that these settings can be unified as an intent-conditioned generative problem, where different prompts specify the desired part decomposition. To this end, we introduce PartLLM, a unified multimodal model that formulates 3D part segmentation as autoregressive semantic decomposition. Conditioned on an input shape and a user prompt, PartLLM autoregressively generates semantic part hypotheses as queries for mask prediction and feeds them to a decomposition-aware decoder that jointly predicts coherent part masks. This unified design supports text-guided part segmentation, interactive segmentation, and full-shape semantic decomposition with controllable granularity within a single model. Extensive experiments across these task settings show that PartLLM consistently outperforms task-specific baselines, demonstrating the effectiveness of unifying 3D part segmentation under an intent-conditioned generative formulation.

Problem

• 3D part segmentation
• unified approach
• intent-conditioned

Innovation

• PartLLM
• unified multimodal model
• intent-conditioned generative problem
• autoregressive semantic decomposition
• decomposition-aware decoder