EI-Part: Explode for Completion and Implode for Refinement

2026-03-14

AI Summary

Existing part-level 3D generation methods often suffer from structural incoherence, geometric implausibility, or insufficient detail. To address these limitations, this work proposes a novel two-stage generation framework that introduces an innovative Explode/Implode dual-state representation strategy. In the Explode stage, the method establishes a coarse part-level structural layout, while the Implode stage refines geometric details with high fidelity. Cross-part feature integration is achieved through a self-attention mechanism, effectively balancing semantic completeness and geometric accuracy. The proposed approach achieves state-of-the-art performance across multiple benchmarks, efficiently generating 3D models that exhibit coherent structures, clear semantic part decomposition, and fine-grained geometric details.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Part-level 3D generation is crucial for various downstream applications, including gaming, film production, and industrial design. However, decomposing a 3D shape into geometrically plausible and meaningful components remains a significant challenge. Previous part-based generation methods often struggle to produce well-constructed parts, exhibiting poor structural coherence, geometric implausibility, inaccuracy, or inefficiency. To address these challenges, we introduce EI-Part, a novel framework specifically designed to generate high-quality 3D shapes with components, characterized by strong structural coherence, geometric plausibility, geometric fidelity, and generation efficiency. We propose utilizing distinct representations at different stages: an Explode state for part completion and an Implode state for geometry refinement. This strategy fully leverages spatial resolution, enabling flexible part completion and fine geometric detail generation. To maintain structural coherence between parts, a self-attention mechanism is incorporated in both exploded and imploded states, facilitating effective information perception and feature fusion among components during generation. Extensive experiments on multiple benchmarks demonstrate that EI-Part efficiently produces semantically meaningful and structurally coherent parts with fine-grained geometric details, achieving state-of-the-art performance in part-level 3D generation. Project page: https://cvhadessun.github.io/EI-Part/

Problem

• part-level 3D generation
• structural coherence
• geometric plausibility
• 3D shape decomposition
• component generation

Innovation

• part-level 3D generation
• Explode-Implode framework
• structural coherence
• self-attention mechanism
• geometric refinement