X-Part: high fidelity and structure coherent shape decomposition

2025-09-10

AI Summary

Existing part-level 3D shape decomposition methods suffer from limited controllability and insufficient semantic plausibility, hindering downstream applications such as retopology, UV mapping, and 3D printing. To address this, we propose a novel interactive part generation paradigm guided by axis-aligned bounding boxes (AABBs): leveraging AABBs as spatial prompting cues, integrating point-wise semantic feature encoding, and incorporating structural consistency optimization to achieve fine-grained decomposition that is semantically coherent, geometrically faithful, and topologically consistent. Our method unifies prompt-driven generative modeling with editable user interaction, enabling intuitive, precise control over part geometry and semantics. Evaluated on standard benchmarks, it achieves state-of-the-art performance in part-level shape generation, with outputs demonstrating production-grade quality and practical usability. To foster reproducibility and further research, we will publicly release the source code.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Generating 3D shapes at part level is pivotal for downstream applications such as mesh retopology, UV mapping, and 3D printing. However, existing part-based generation methods often lack sufficient controllability and suffer from poor semantically meaningful decomposition. To this end, we introduce X-Part, a controllable generative model designed to decompose a holistic 3D object into semantically meaningful and structurally coherent parts with high geometric fidelity. X-Part exploits the bounding box as prompts for the part generation and injects point-wise semantic features for meaningful decomposition. Furthermore, we design an editable pipeline for interactive part generation. Extensive experimental results show that X-Part achieves state-of-the-art performance in part-level shape generation. This work establishes a new paradigm for creating production-ready, editable, and structurally sound 3D assets. Codes will be released for public research.

Problem

• Generating 3D shapes with semantically meaningful part decomposition
• Achieving high geometric fidelity in part-level shape generation
• Providing controllable and editable 3D part generation pipeline

Innovation

• Controllable generative model for 3D part decomposition
• Uses bounding box prompts and semantic feature injection
• Editable pipeline enabling interactive part generation