mlsanityData to 7 Oct 2026

Equivariant Neural Rendering

arXiv 2006.07630 ↗First posted 13 Jun 2020cs.CV stat.MLcited by 47

Not on the map. Why?

Abstract (arXiv)

We propose a framework for learning neural scene representations directly from images, without 3D supervision. Our key insight is that 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. Specifically, we introduce a loss which enforces equivariance of the scene representation with respect to 3D transformations. Our formulation allows us to infer and render scenes in real time while achieving comparable results to models requiring minutes for inference. In addition, we introduce two challenging new datasets for scene representation and neural rendering, including scenes with complex lighting and backgrounds. Through experiments, we show that our model achieves compelling results on these datasets as well as on standard ShapeNet benchmarks.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 15; 2023: 9; 2024: 6; 2025: 2; 2026: 3.

47 papers.

Sort:

By area:

  1. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  2. 2022Novel View Synthesis with Diffusion Modelscited by 299
  3. 2021COIN: COmpression with Implicit Neural representationscited by 232
  4. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  5. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  6. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
  7. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  8. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  9. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  10. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  11. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 91
  12. 2021Generative Models as Distributions of Functionscited by 89
35 more
  1. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  2. 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
  3. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  4. 2022Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenescited by 43
  5. 2022Transframer: Arbitrary Frame Prediction with Generative Modelscited by 37
  6. 2021Fast and Explicit Neural View Synthesiscited by 28
  7. 2022Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolationcited by 26
  8. 2022Equivariant Representation Learning via Class-Pose Decompositioncited by 17
  9. 2022Neural Groundplans: Persistent Neural Scene Representations from a Single Imagecited by 17
  10. 2021Addressing the Topological Defects of Disentanglement via Distributed Operatorscited by 14
  11. 2022SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesiscited by 13
  12. 2023Neural Fourier Transform: A General Approach to Equivariant Representation Learningcited by 12
  13. 2022Learning Generalizable Light Field Networks from Few Imagescited by 10
  14. 2024On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theorycited by 10
  15. 2021Unsupervised Novel View Synthesis from a Single Imagecited by 8
  16. 2023InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modulescited by 7
  17. 2024CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesiscited by 6
  18. 2021Hamiltonian latent operators for content and motion disentanglement in image sequencescited by 5
  19. 2023Learning Interpretable Low-dimensional Representation via Physical Symmetrycited by 4
  20. 2023Topological Obstructions and How to Avoid Themcited by 4
  21. 2023VaLID: Variable-Length Input Diffusion for Novel View Synthesiscited by 4
  22. 2023Unsupervised Coordinate-Based Video Denoisingcited by 3
  23. 2024G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Imagescited by 3
  24. 2024See360: Novel Panoramic View Interpolationcited by 2
  25. 2021Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networkscited by 1
  26. 2022Equivariant Light Field Convolution and Transformercited by 1
  27. 2024ViewFusion: Learning Composable Diffusion Models for Novel View Synthesiscited by 1
  28. 2025A Survey on World Models Grounded in Acoustic Physical Informationcited by 1
  29. 2026Constructing VAE Latent Spaces with Prescribed Topologycited by 1
  30. 2021Self-Supervised Equivariant Scene Synthesis from Videocited by 0
  31. 2022Capabilities, Limitations and Challenges of Style Transfer with CycleGANs: A Study on Automatic Ring Design Generationcited by 0
  32. 2023Equivariant Representation Learning in the Presence of Stabilizerscited by 0
  33. 2025Learning Group Actions In Disentangled Latent Image Representationscited by 0
  34. 2026Latent Equivariant Operators for Robust Object Recognition: Promises and Challengescited by 0
  35. 2026Equivariant Latent Alignment via Flow Matching under Group Symmetriescited by 0