mlsanityData to 7 Oct 2026

Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision

arXiv 1912.07372 ↗First posted 16 Dec 2019cs.CV cs.LG eess.IVcited by 699

Not on the map. Why?

Abstract (arXiv)

Learning-based 3D reconstruction methods have shown impressive results. However, most methods require 3D supervision which is often hard to obtain for real-world datasets. Recently, several works have proposed differentiable rendering techniques to train reconstruction models from RGB images. Unfortunately, these approaches are currently restricted to voxel- and mesh-based representations, suffering from discretization or low resolution. In this work, we propose a differentiable rendering formulation for implicit shape and texture representations. Implicit representations have recently gained popularity as they represent shape and texture continuously. Our key insight is that depth gradients can be derived analytically using the concept of implicit differentiation. This allows us to learn implicit shape and texture representations directly from RGB images. We experimentally show that our single-view reconstructions rival those learned with full 3D supervision. Moreover, we find that our method can be used for multi-view 3D reconstruction, directly resulting in watertight meshes.

Key facts. Cited by 699 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 128; 2022: 187; 2023: 190; 2024: 122; 2025: 52; 2026: 20.

699 papers.

Sort:

By area:

  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  5. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  6. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  7. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  9. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  10. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  11. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  12. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
38 more
  1. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  2. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  3. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  4. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  5. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  6. 2021Neural Fields in Visual Computing and Beyondcited by 539
  7. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  8. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  9. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  10. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  11. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  12. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  13. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  14. 2023Gaussian Splatting SLAMcited by 410
  15. 2022Kubric: A scalable dataset generatorcited by 373
  16. 2021Advances in Neural Renderingcited by 365
  17. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  18. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  19. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  20. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  21. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  22. 2021Neural RGB-D Surface Reconstructioncited by 312
  23. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  24. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  25. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  26. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  27. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  28. 2021NeRV: Neural Representations for Videoscited by 255
  29. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  30. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  31. 2021Editing Conditional Radiance Fieldscited by 222
  32. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  33. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  34. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  35. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  36. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  37. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  38. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 204

50 most cited of 699 All 699 (JSON)