SemanticGarment: Semantic-Controlled Generation and Editing of 3D Gaussian Garments

2025-09-21

AI Summary

Existing 3D garment generation methods suffer from limited multi-view consistency, geometric/texture fidelity, and editing flexibility. To address these challenges, we propose a semantic-driven 3D garment generation and editing framework built upon 3D Gaussian Splatting. Our method integrates structured human priors with fine-grained garment semantics—eliminating the need for predefined mesh templates or manual rigging—while introducing a self-occlusion-aware optimization strategy that effectively mitigates holes and artifacts in single-image reconstruction. It supports high-fidelity global and local editing driven by text or image prompts, enabling multi-view-consistent, wear-aware 3D garment synthesis. Experiments demonstrate superior performance over state-of-the-art approaches in generation quality, editing efficiency, and interactivity. Our work establishes a new paradigm for photorealistic, customizable digital garment generation.

Technology Category

• Computer Vision: 3D Computer Vision
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Search and Optimization: Sampling/Simulation-based Search

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: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

3D digital garment generation and editing play a pivotal role in fashion design, virtual try-on, and gaming. Traditional methods struggle to meet the growing demand due to technical complexity and high resource costs. Learning-based approaches offer faster, more diverse garment synthesis based on specific requirements and reduce human efforts and time costs. However, they still face challenges such as inconsistent multi-view geometry or textures and heavy reliance on detailed garment topology and manual rigging. We propose SemanticGarment, a 3D Gaussian-based method that realizes high-fidelity 3D garment generation from text or image prompts and supports semantic-based interactive editing for flexible user customization. To ensure multi-view consistency and garment fitting, we propose to leverage structural human priors for the generative model by introducing a 3D semantic clothing model, which initializes the geometry structure and lays the groundwork for view-consistent garment generation and editing. Without the need to regenerate or rely on existing mesh templates, our approach allows for rapid and diverse modifications to existing Gaussians, either globally or within a local region. To address the artifacts caused by self-occlusion for garment reconstruction based on single image, we develop a self-occlusion optimization strategy to mitigate holes and artifacts that arise when directly animating self-occluded garments. Extensive experiments are conducted to demonstrate our superior performance in 3D garment generation and editing.

Problem

• Achieving multi-view consistent 3D garment generation from text or image prompts
• Enabling semantic-based interactive editing without regenerating mesh templates
• Addressing self-occlusion artifacts in single-image garment reconstruction

Innovation

• 3D Gaussian-based method for garment generation
• Leverages structural human priors for consistency
• Self-occlusion optimization for single-image reconstruction