通过表面正则化提升NeRF几何精度，让光照与形状更真实一致。
Surf-NeRF: Surface Regularised Neural Radiance Fields
- 引入四种正则项约束几何平滑、法向一致性及漫反射/镜面反射分离。
- 相比传统网格NeRF，法向误差降低28%，更贴近真实场景几何。
- 兼容现有NeRF结构，适合对几何精度要求高的三维重建应用。
神经辐射场（NeRF）能提供高保真、连续的场景表示，真实还原光照行为。尽管如Ref-NeRF等方法通过物理启发模型改进几何，但NeRF仍难以克服形状-辐射模糊问题，难以收敛到与真实几何一致的表示。本文表明，采用表面光场模型的课程学习策略，并结合基于格网的哈希编码，可促使NeRF更准确地逼近几何真实场景。我们提出四项正则化项，分别强制几何平滑性、法向一致性以及在场景几何处实现漫反射与镜面反射外观的分离，符合物理模型。所提方法使法向估计精度比传统网格式NeRF（带反射参数化）提升28%。该方法更精确地区分视角依赖外观，引导NeRF生成与真实场景一致的几何表示。实验验证了其与现有NeRF变体的良好兼容性，是推动基于辐射表示应用于几何敏感任务的关键一步。
原文摘要 · Abstract (English)
Neural Radiance Fields (NeRFs) provide a high fidelity, continuous scene representation that can realistically represent complex behaviour of light. Despite works like Ref-NeRF improving geometry through physics-inspired models, the ability for a NeRF to overcome shape-radiance ambiguity and converge to a representation consistent with real geometry remains limited. We demonstrate how both curriculum learning of a surface light field model and using a lattice-based hash encoding helps a NeRF converge towards a more geometrically accurate scene representation. We introduce four regularisation terms to impose geometric smoothness, consistency of normals, and a separation of Lambertian and specular appearance at geometry in the scene, conforming to physical models. Our approach yields 28% more accurate normals than traditional grid-based NeRF variants with reflection parameterisation. Our approach more accurately separates view-dependent appearance, conditioning a NeRF to have a geometric representation consistent with the captured scene. We demonstrate compatibility of our method with existing NeRF variants, as a key step in enabling radiance-based representations for geometry critical applications.
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。