LaFiTe: A Generative Latent Field for 3D Native Texturing

TL;DR

LaFiTe introduces a novel generative framework for high-fidelity, seamless 3D surface texturing using a sparse latent color field, significantly surpassing existing methods in quality and versatility.

Contribution

The paper presents LaFiTe, a new 3D generative model employing a variational autoencoder and rectified-flow for superior native texturing, addressing the lack of effective latent representations.

Findings

Achieves >10 dB PSNR improvement over state-of-the-art methods.

Enables high-quality, style-coherent texture synthesis across diverse geometries.

Supports applications like material synthesis and texture super-resolution.

Abstract

Generating high-fidelity, seamless textures directly on 3D surfaces, what we term 3D-native texturing, remains a fundamental open challenge, with the potential to overcome long-standing limitations of UV-based and multi-view projection methods. However, existing native approaches are constrained by the absence of a powerful and versatile latent representation, which severely limits the fidelity and generality of their generated textures. We identify this representation gap as the principal barrier to further progress. We introduce LaFiTe, a framework that addresses this challenge by learning to generate textures as a 3D generative sparse latent color field. At its core, LaFiTe employs a variational autoencoder (VAE) to encode complex surface appearance into a sparse, structured latent space, which is subsequently decoded into a continuous color field. This representation achieves unprecedented fidelity, exceeding state-of-the-art methods by >10 dB PSNR in reconstruction, by effectively disentangling texture appearance from mesh topology and UV parameterization. Building upon this strong representation, a conditional rectified-flow model synthesizes high-quality, coherent textures across diverse styles and geometries. Extensive experiments demonstrate that LaFiTe not only sets a new benchmark for 3D-native texturing but also enables flexible downstream applications such as material synthesis and texture super-resolution, paving the way for the next generation of 3D content creation workflows.