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

TL;DR

TexSpot introduces a novel 3D texture enhancement framework that combines point-based and UV-based representations, using a diffusion transformer conditioned on Texlets to improve the quality and consistency of 3D textures.

Contribution

The paper proposes Texlet, a new 3D texture representation, and a diffusion-based framework for high-quality, view-consistent 3D texture enhancement.

Findings

Significantly improves visual fidelity of 3D textures.

Enhances geometric consistency and robustness.

Outperforms existing state-of-the-art methods.

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://texlet-arch.github.io/TexSpot-page.