用神经网络从乱拍照片中恢复真实材质，让3D模型光照重演更逼真。
DANTE-W: Diffuse Albedo Neural Texturing in the Wild
- 用神经网络融合多视角图像，生成统一材质贴图
- 在真实场景和合成物体上均实现高保真材质重建
- 适合需要真实光照重演的3D建模与数字孪生应用
传统网格贴图直接拼合多视角图像，不可避免地引入固有阴影与投影阴影，影响光照重演时的视觉质量。为此，我们提出神经贴图框架DANTE-W，可从非结构化图像集合中恢复大尺度野外场景的高保真漫反射材质贴图，并无缝集成至传统3D重建流程。给定重构的网格及其表面参数化，本方法通过表达能力强的神经表示，将视空间生成式材质先验融合至一致的纹理空间，同时借助物理合理神经渲染显著增强细粒度纹理细节。为全面评估方法，我们构建了一个包含多样、精细纹理的基准数据集，涵盖真实野外场景与合成物体。大量实验验证了该方法在准确重建材质贴图及提升光照重演保真度方面的有效性。项目页面：dante-wild.github.io。
原文摘要 · Abstract (English)
Classical mesh texturing techniques blend captured multi-view images directly, which inevitably suffer from baked-in shading and casted shadows that compromise visual fidelity during relighting. To circumvent this issue, we present a neural texturing framework, namely DANTE-W, to enable high-fidelity diffuse albedo texture recovery from unstructured image collections for large-scale, in-the-wild scenes, which integrates seamlessly with traditional 3D reconstruction pipelines. Given a reconstructed mesh and its surface parameterization, our method fuses view-space generative albedo priors into a coherent texture space via an expressive neural representation, while substantially enhancing fine-grained textural details through physically principled neural rendering. To comprehensively evaluate our method, we curate a benchmark dataset featuring diverse, fine-grained textures, comprising both real-world in-the-wild scenes and synthetic objects. Extensive experiments verify the effectiveness of our approach in reconstructing accurate albedo textures and boosting relighting fidelity. Project page: dante-wild.github.io.
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。