Differentiable Shadow Mapping for Efficient Inverse Graphics
Not on the map. Why?
Abstract (arXiv)
We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering from the perspective of a light, can be combined with existing differentiable rasterizers to yield differentiable visibility information. We demonstrate at several inverse graphics problems that differentiable shadow maps are orders of magnitude faster than differentiable light transport simulation with similar accuracy -- while differentiable rasterization without shadows often fails to converge.
Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 40 of its 100 references that are in the map. First posted on arXiv 21 Aug 2023.
Builds on
40 of 100 references.
References · 40
- 2014Adam: A Method for Stochastic Optimizationcited by 37,093
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,021
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,958
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,706
- 2021Volume Rendering of Neural Implicit Surfacescited by 992
- 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
- 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 644
- 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
- 2020Modular Primitives for High-Performance Differentiable Renderingcited by 440
- 2017Neural 3D Mesh Renderercited by 437
- 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
28 more
- 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 364
- 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 334
- 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 333
- 20193D Morphable Face Models -- Past, Present and Futurecited by 269
- 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
- 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
- 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
- 2022Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoisingcited by 163
- 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
- 2021Real-time Deep Dynamic Characterscited by 133
- 2022IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Imagescited by 111
- 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
- 2020Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Renderingcited by 101
- 2020Learning Formation of Physically-Based Face Attributescited by 94
- 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
- 2021Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Renderingcited by 71
- 2020Convolutional Generation of Textured 3D Meshescited by 52
- 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
- 2021AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANscited by 49
- 2022Multi-View Mesh Reconstruction with Neural Deferred Shadingcited by 44
- 2022Differentiable Rendering of Neural SDFs through Reparameterizationcited by 26
- 2021Appearance-Driven Automatic 3D Model Simplificationcited by 24
- 2022Dr.Jit: A Just-In-Time Compiler for Differentiable Renderingcited by 16
- 2022GenDR: A Generalized Differentiable Renderercited by 12
- 2021Efficient and Differentiable Shadow Computation for Inverse Problemscited by 11
- 2021Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objectscited by 10
- 2021Shadow Art Revisited: A Differentiable Rendering Based Approachcited by 10
- 2022Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterizationcited by 2
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 2.
4 papers.
- 2023The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibilitycited by 11
- 2024All-frequency Full-body Human Image Relightingcited by 3
- 2026SRUG: Shadow-Guided Relightable Urban Scene with Generation Modelcited by 0
- 2026SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illuminationcited by 0
- 2026SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination9 Sep 2026
- 2026SRUG: Shadow-Guided Relightable Urban Scene with Generation Model23 May 2026
- 2024All-frequency Full-body Human Image Relighting1 Nov 2024
- 2023The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility28 Nov 2023