Advances in Neural 3D Mesh Texturing: A Survey

2026-05-28

AI Summary

This paper addresses the longstanding challenge of balancing visual realism and computational efficiency in 3D mesh texturing by providing a systematic survey of recent advances in neural texture generation. It introduces a unified classification framework that encompasses methods ranging from early generative adversarial networks (GANs) to modern diffusion models, integrating core technical components such as mesh geometry processing, texture mapping, differentiable rendering, and neural synthesis. The work comprehensively traces the evolution of research in texture synthesis, transfer, and completion, while establishing a structured taxonomy of learning-based approaches. Furthermore, it clarifies prevailing supervision strategies, benchmark datasets, and evaluation metrics, and concludes with a critical discussion of current limitations and promising future directions, offering a cohesive reference for the growing field of learning-driven 3D texture generation.

Abstract

Texturing 3D meshes plays a vital role in determining the visual realism of digital objects and scenes. Although recent generative 3D approaches based on Neural Radiance Fields and Gaussian Splatting can produce textured assets directly, polygonal meshes remain the core representation across modeling, animation, visual effects, and gaming pipelines. Neural 3D mesh texturing therefore continues to be an essential and active area of research. In this survey, we present a comprehensive review of recent advances in neural 3D mesh texturing, covering methods for texture synthesis, transfer, and completion. We first summarize key foundations in mesh geometry, texture mapping, differentiable rendering, and neural generative models, and then organize the literature into a unified taxonomy spanning early GAN-based methods to modern diffusion-based pipelines. We further analyze common architectures and supervision strategies, review datasets and evaluation protocols, and discuss emerging applications, practical/commercial systems, and open challenges. Together, these insights provide a structured perspective on the current landscape and help guide future developments in learning-based 3D mesh texturing.

Problem

• Neural 3D mesh texturing
• Texture synthesis
• Texture transfer
• Texture completion
• Visual realism

Innovation

• Neural 3D Mesh Texturing
• Texture Synthesis
• Diffusion Models
• Differentiable Rendering
• Generative Models