系统梳理神经3D网格贴图最新进展，助力高真实感数字资产生成
Advances in Neural 3D Mesh Texturing: A Survey
- 构建统一分类体系，涵盖从GAN到扩散模型的贴图方法
- 分析主流架构与监督策略，总结关键数据集与评估标准
- 适合关注3D内容生成、游戏与影视工业应用的研究者
贴图对数字物体和场景的视觉真实感至关重要。尽管基于神经辐射场和高斯溅射的生成式3D方法可直接产出带纹理资产，但多边形网格仍在建模、动画、视觉特效和游戏流程中占据核心地位。因此，神经3D网格贴图仍是重要且活跃的研究领域。本文全面综述了神经3D网格贴图的最新进展，涵盖纹理生成、迁移与补全方法。首先总结网格几何、贴图映射、可微渲染及神经生成模型的基础知识，随后将文献归纳为统一分类体系，贯穿早期基于GAN的方法到现代扩散模型流水线。进一步分析常见架构与监督策略，回顾数据集与评估协议，探讨新兴应用、实用/商业系统及开放挑战。这些洞察为学习型3D网格贴图研究提供了结构化视角，有助于指引未来发展方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。