用生成式光照重建可任意重光的3D物体，无需逐光照优化。
ROGR: Relightable 3D Objects using Generative Relighting
- 通过生成式光照采样构建数据集，训练光照条件神经辐射场。
- 在TensoIR和Stanford-ORB数据集上优于现有方法，支持实时重光。
- 适合需要真实感3D重光的数字内容创作与虚拟展示场景。
我们提出ROGR，一种从多视角图像重建可重光3D物体的新方法。该方法利用生成式光照模型模拟物体在新环境光照下的外观，通过采样多种光照环境生成数据集，训练光照条件神经辐射场（NeRF）。该NeRF采用双分支结构，分别编码通用光照效应与镜面反射。优化后的模型可直接前向传播实现任意环境贴图下的高效重光，无需每种光照单独优化或光传输模拟。我们在公认的TensoIR和Stanford-ORB数据集上评估，多数指标超越当前最优方法，并展示了真实物体捕获的应用效果。
原文摘要 · Abstract (English)
We introduce ROGR, a novel approach that reconstructs a relightable 3D model of an object captured from multiple views, driven by a generative relighting model that simulates the effects of placing the object under novel environment illuminations. Our method samples the appearance of the object under multiple lighting environments, creating a dataset that is used to train a lighting-conditioned Neural Radiance Field (NeRF) that outputs the object's appearance under any input environmental lighting. The lighting-conditioned NeRF uses a novel dual-branch architecture to encode the general lighting effects and specularities separately. The optimized lighting-conditioned NeRF enables efficient feed-forward relighting under arbitrary environment maps without requiring per-illumination optimization or light transport simulation. We evaluate our approach on the established TensoIR and Stanford-ORB datasets, where it improves upon the state-of-the-art on most metrics, and showcase our approach on real-world object captures.
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。