TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation

2026-02-12

AI Summary

Existing multi-view diffusion methods often struggle to generate high-fidelity 3D textures due to view inconsistency, UV mapping distortions, and limitations imposed by point cloud density. To address these challenges, this work proposes TexSpot, a novel framework that introduces Texlet—a spatially uniform latent point representation that decouples texture quality from geometric density. TexSpot integrates a 2D encoder to capture local texture details and a 3D encoder to incorporate global shape context, followed by a cascaded 3D-to-2D decoder for texture reconstruction. A diffusion Transformer, conditioned on Texlets, is then trained to enhance texture fidelity. Experimental results demonstrate that TexSpot significantly outperforms current state-of-the-art methods in terms of visual fidelity, geometric consistency, and robustness.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing representations either rely on UV maps, which suffer from distortion during unwrapping, or point-based methods, which tightly couple texture fidelity to geometric density that limits high-resolution texture generation. To address these limitations, we introduce TexSpot, a diffusion-based texture enhancement framework. At its core is Texlet, a novel 3D texture representation that merges the geometric expressiveness of point-based 3D textures with the compactness of UV-based representation. Each Texlet latent vector encodes a local texture patch via a 2D encoder and is further aggregated using a 3D encoder to incorporate global shape context. A cascaded 3D-to-2D decoder reconstructs high-quality texture patches, enabling the Texlet space learning. Leveraging this representation, we train a diffusion transformer conditioned on Texlets to refine and enhance textures produced by multi-view diffusion methods. Extensive experiments demonstrate that TexSpot significantly improves visual fidelity, geometric consistency, and robustness over existing state-of-the-art 3D texture generation and enhancement approaches. Project page: https://anonymous.4open.science/w/TexSpot-page-2D91.

Problem

• 3D texture generation
• view-inconsistency
• UV maps
• point-based representation
• texture fidelity

Innovation

• Texlet
• 3D texture enhancement
• diffusion transformer
• spatially-uniform representation
• multi-view consistency