mlsanityData to 14 Oct 2026

Differentiable Rendering of Neural SDFs through Reparameterization

arXiv 2206.05344 ↗First posted 10 Jun 2022cs.GR cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

We present a method to automatically compute correct gradients with respect to geometric scene parameters in neural SDF renderers. Recent physically-based differentiable rendering techniques for meshes have used edge-sampling to handle discontinuities, particularly at object silhouettes, but SDFs do not have a simple parametric form amenable to sampling. Instead, our approach builds on area-sampling techniques and develops a continuous warping function for SDFs to account for these discontinuities. Our method leverages the distance to surface encoded in an SDF and uses quadrature on sphere tracer points to compute this warping function. We further show that this can be done by subsampling the points to make the method tractable for neural SDFs. Our differentiable renderer can be used to optimize neural shapes from multi-view images and produces comparable 3D reconstructions to recent SDF-based inverse rendering methods, without the need for 2D segmentation masks to guide the geometry optimization and no volumetric approximations to the geometry.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 21 of its 59 references that are in the map. First posted on arXiv 10 Jun 2022.

Builds on

21 of 59 references.

References · 21

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  3. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  4. 2020Neural Sparse Voxel Fieldscited by 959
  5. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  6. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  7. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  8. 2021Neural Fields in Visual Computing and Beyondcited by 540
  9. 2017Neural 3D Mesh Renderercited by 437
  10. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  11. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  12. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
9 more
  1. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  2. 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
  3. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  4. 2020MeshSDF: Differentiable Iso-Surface Extractioncited by 112
  5. 2021Neural Lumigraph Renderingcited by 105
  6. 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
  7. 2016A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimationcited by 42
  8. 2021Differentiable Surface Rendering via Non-Differentiable Samplingcited by 28
  9. 2019Differentiable Visual Computingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 10; 2024: 9; 2025: 3; 2026: 2.

26 papers.

Sort:

  1. 2023Neural-PBIR Reconstruction of Shape, Material, and Illuminationcited by 45
  2. 2024IllumiNeRF: 3D Relighting Without Inverse Renderingcited by 29
  3. 2023Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimationcited by 23
  4. 2022ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervisioncited by 17
  5. 2023Eclipse: Disambiguating Illumination and Materials using Unintended Shadowscited by 14
  6. 2024Rasterized Edge Gradients: Handling Discontinuities Differentiablycited by 14
  7. 2024NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Renderingcited by 8
  8. 2024HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Conditioncited by 8
  9. 2024A Simple Approach to Differentiable Rendering of SDFscited by 7
  10. 2024DiffCSG: Differentiable CSG via Rasterizationcited by 7
  11. 2023A Theory of Topological Derivatives for Inverse Rendering of Geometrycited by 6
  12. 20223D Neural Sculpting (3DNS): Editing Neural Signed Distance Functionscited by 4
14 more
  1. 2023Differentiable Shadow Mapping for Efficient Inverse Graphicscited by 4
  2. 2026DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplificationcited by 4
  3. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  4. 2023PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstructioncited by 3
  5. 2024Many-Worlds Inverse Renderingcited by 3
  6. 2023RNA: Relightable Neural Assetscited by 2
  7. 2023Single-view 3D reconstruction via inverse procedural modelingcited by 1
  8. 2023Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Mapscited by 1
  9. 2024Differentiable Convex Polyhedra Optimization from Multi-view Imagescited by 1
  10. 2025Interactive Stroke-based Neural SDF Sculptingcited by 1
  11. 2024Probabilistic Directed Distance Fields for Ray-Based Shape Representationscited by 0
  12. 2025Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splattingcited by 0
  13. 2025Automated design of compound lenses with discrete-continuous optimizationcited by 0
  14. 2026GradInf: Gradient Estimation as Probabilistic Inferencecited by 0