mlsanityData to 7 Oct 2026

GenDR: A Generalized Differentiable Renderer

arXiv 2204.13845 ↗First posted 29 Apr 2022cs.CV cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component. We instantiate our general differentiable renderer, which generalizes existing differentiable renderers like SoftRas and DIB-R, with an array of different smoothing distributions to cover a large spectrum of reasonable settings. We evaluate an array of differentiable renderer instantiations on the popular ShapeNet 3D reconstruction benchmark and analyze the implications of our results. Surprisingly, the simple uniform distribution yields the best overall results when averaged over 13 classes; in general, however, the optimal choice of distribution heavily depends on the task.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

24 of 37 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  4. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  6. 2017Neural 3D Mesh Renderercited by 437
  7. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  8. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
  9. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  10. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  11. 2020Differentiable Rendering: A Surveycited by 123
  12. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
12 more
  1. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  2. 2020Analyzing Differentiable Fuzzy Logic Operatorscited by 100
  3. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  4. 2020Learning with Differentiable Perturbed Optimizerscited by 81
  5. 2020Leveraging 2D Data to Learn Textured 3D Mesh Generationcited by 69
  6. 2016A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimationcited by 42
  7. 2021Learning with Algorithmic Supervision via Continuous Relaxationscited by 21
  8. 2019Pix2Vex: Image-to-Geometry Reconstruction using a Smooth Differentiable Renderercited by 18
  9. 2017Material Editing Using a Physically Based Rendering Networkcited by 17
  10. 2021Differentiable Rendering with Perturbed Optimizerscited by 7
  11. 2021Style Agnostic 3D Reconstruction via Adversarial Style Transfercited by 3
  12. 2018Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderercited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 3; 2025: 1; 2026: 2.

12 papers.

  1. 2022Deep Differentiable Logic Gate Networkscited by 67
  2. 2022Plateau-reduced Differentiable Path Tracingcited by 10
  3. 2024Uncertainty Quantification via Stable Distribution Propagationcited by 10
  4. 2023Differentiable Shadow Mapping for Efficient Inverse Graphicscited by 4
  5. 2024Marrying NeRF with Feature Matching for One-step Pose Estimationcited by 3
  6. 2024Newton Losses: Using Curvature Information for Learning with Differentiable Algorithmscited by 2
  7. 2026SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradientscited by 2
  8. 2023High-Quality Real-Time Rendering Using Subpixel Sampling Reconstructioncited by 1
  9. 2023Differentiable Radio Frequency Ray Tracing for Millimeter-Wave Sensingcited by 1
  10. 2026Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twincited by 1
  11. 2022Learning to Rasterize Differentiablycited by 0
  12. 2025Light Transport-aware Diffusion Posterior Sampling for Single-View Reconstruction of 3D Volumescited by 0