Eclipse: Disambiguating Illumination and Materials Using Unintended Shadows
Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Todd E. Zickler, Pratul P. Srinivasan
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2e6639b5-576f-40f3-86dd-e5d860807871Cited by top-tier papers10
- IllumiNeRF: 3D Relighting Without Inverse RenderingXiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park et al.NeurIPS 2024 · 34 citations
- Spherical Voronoi: Directional Appearance as a Differentiable Partition of the SphereFrancesco Di Sario, Daniel Rebain, Dor Verbin, Marco Grangetto et al.CVPR 2026 · 13 citations
- StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian SplattingShakiba Kheradmand, Delio Vicini, George Kopanas, Dmitry Lagun et al.ICCV 2025 · 7 citations
- LAENeRF: Local Appearance Editing for Neural Radiance FieldsLukas Radl, Michael Steiner, Andreas Kurz, Markus SteinbergerCVPR 2024 · 6 citations
- Practical Inverse Rendering of Textured and Translucent AppearancePhilippe Weier, Jérémy Riviere, Ruslan Guseinov, Stephan J. Garbin et al.SIGGRAPH 2025 · 3 citations
Builds on15
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional DomainsMatthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil et al.NeurIPS 2020 · 4,036 citations
- NeRD: Neural Reflectance Decomposition from Image CollectionsMark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron et al.ICCV 2021 · 608 citations
- Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance FieldsDor Verbin, Peter Hedman, Ben Mildenhall, Todd E. Zickler et al.CVPR 2022 · 477 citations
- Extracting Triangular 3D Models, Materials, and Lighting From ImagesJacob Munkberg, Wenzheng Chen, Jon Hasselgren, Alex Evans et al.CVPR 2022 · 306 citations
Related papers
- Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingJon Hasselgren, Nikolai Hofmann, Jacob MunkbergNeurIPS 2022 · 234 citations
- Modeling Indirect Illumination for Inverse RenderingYuanqing Zhang, Jiaming Sun, Xingyi He, Huan Fu et al.CVPR 2022 · 140 citations
- What You Can Reconstruct from a ShadowRuoshi Liu, Sachit Menon, Chengzhi Mao, Dennis Park et al.CVPR 2023
- NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect IlluminationHaoqian Wu, Zhipeng Hu, Lincheng Li, Yongqiang Zhang et al.CVPR 2023
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy ObjectsYue Fan, Ningjing Fan, Ivan Skorokhodov, Oleg Voynov et al.CVPR 2025
