Eclipse: Disambiguating Illumination and Materials Using Unintended Shadows
Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Todd E. Zickler, Pratul P. Srinivasan
摘要
Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This problem is especially challenging for diffuse objects: it is ill-conditioned because diffuse materials severely blur incoming light, and it is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination-even from diffuse objects-by exploiting unintended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatiallyvarying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who inadvertently cast shadows upon it.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper10
- IllumiNeRF: 3D Relighting Without Inverse RenderingXiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park 等NeurIPS 2024 · 被引用 34 次
- Spherical Voronoi: Directional Appearance as a Differentiable Partition of the SphereFrancesco Di Sario, Daniel Rebain, Dor Verbin, Marco Grangetto 等CVPR 2026 · 被引用 13 次
- StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian SplattingShakiba Kheradmand, Delio Vicini, George Kopanas, Dmitry Lagun 等ICCV 2025 · 被引用 7 次
- LAENeRF: Local Appearance Editing for Neural Radiance FieldsLukas Radl, Michael Steiner, Andreas Kurz, Markus SteinbergerCVPR 2024 · 被引用 6 次
- Practical Inverse Rendering of Textured and Translucent AppearancePhilippe Weier, Jérémy Riviere, Ruslan Guseinov, Stephan J. Garbin 等SIGGRAPH 2025 · 被引用 3 次
它引用的顶会 Paper15
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional DomainsMatthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil 等NeurIPS 2020 · 被引用 4,036 次
- NeRD: Neural Reflectance Decomposition from Image CollectionsMark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron 等ICCV 2021 · 被引用 608 次
- Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance FieldsDor Verbin, Peter Hedman, Ben Mildenhall, Todd E. Zickler 等CVPR 2022 · 被引用 477 次
- Extracting Triangular 3D Models, Materials, and Lighting From ImagesJacob Munkberg, Wenzheng Chen, Jon Hasselgren, Alex Evans 等CVPR 2022 · 被引用 306 次
相关 Paper
- Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingJon Hasselgren, Nikolai Hofmann, Jacob MunkbergNeurIPS 2022 · 被引用 234 次
- Modeling Indirect Illumination for Inverse RenderingYuanqing Zhang, Jiaming Sun, Xingyi He, Huan Fu 等CVPR 2022 · 被引用 140 次
- What You Can Reconstruct from a ShadowRuoshi Liu, Sachit Menon, Chengzhi Mao, Dennis Park 等CVPR 2023
- NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect IlluminationHaoqian Wu, Zhipeng Hu, Lincheng Li, Yongqiang Zhang 等CVPR 2023
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy ObjectsYue Fan, Ningjing Fan, Ivan Skorokhodov, Oleg Voynov 等CVPR 2025
