PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image

2025-07-23

AI Summary

Existing single-image 3D human reconstruction methods suffer from inter-part texture misalignment (e.g., jacket-pants texture bleeding), resulting in inconsistent and implausible textures. To address this, we propose a part-structure-aware texture alignment framework. First, we introduce a texture-free, surface-driven 3D part segmentation module that yields geometrically coherent anatomical partitions. Second, we design a part-guided texture generation module that leverages pretrained text-to-image diffusion models (e.g., Stable Diffusion) to synthesize high-fidelity, semantically appropriate textures independently for each body part. By bypassing conventional UV parameterization, our approach eliminates texture stretching and seam artifacts. Evaluated on multiple benchmarks, our method achieves state-of-the-art reconstruction quality, significantly improving texture consistency, part-wise independence, and visual realism.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

The misaligned human texture across different human parts is one of the main limitations of existing 3D human reconstruction methods. Each human part, such as a jacket or pants, should maintain a distinct texture without blending into others. The structural coherence of human parts serves as a crucial cue to infer human textures in the invisible regions of a single image. However, most existing 3D human reconstruction methods do not explicitly exploit such part segmentation priors, leading to misaligned textures in their reconstructions. In this regard, we present PARTE, which utilizes 3D human part information as a key guide to reconstruct 3D human textures. Our framework comprises two core components. First, to infer 3D human part information from a single image, we propose a 3D part segmentation module (PartSegmenter) that initially reconstructs a textureless human surface and predicts human part labels based on the textureless surface. Second, to incorporate part information into texture reconstruction, we introduce a part-guided texturing module (PartTexturer), which acquires prior knowledge from a pre-trained image generation network on texture alignment of human parts. Extensive experiments demonstrate that our framework achieves state-of-the-art quality in 3D human reconstruction. The project page is available at https://hygenie1228.github.io/PARTE/.

Problem

• Misaligned textures in 3D human reconstruction from single images
• Lack of part segmentation priors in existing methods
• Inferring human textures in invisible image regions

Innovation

• Uses 3D part segmentation for textureless surface
• Integrates part-guided texturing with prior knowledge
• Leverages pre-trained networks for texture alignment