mlsanityData to 14 Oct 2026

SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene

arXiv 2211.17260 ↗First posted 30 Nov 2022cs.CV cs.AI cs.GRcited by 11

Not on the map. Why?

Abstract (arXiv)

Generative models have shown great promise in synthesizing photorealistic 3D objects, but they require large amounts of training data. We introduce SinGRAF, a 3D-aware generative model that is trained with a few input images of a single scene. Once trained, SinGRAF generates different realizations of this 3D scene that preserve the appearance of the input while varying scene layout. For this purpose, we build on recent progress in 3D GAN architectures and introduce a novel progressive-scale patch discrimination approach during training. With several experiments, we demonstrate that the results produced by SinGRAF outperform the closest related works in both quality and diversity by a large margin.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 47 of its 60 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

47 of 60 references.

References · 47

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  8. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  11. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  12. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
35 more
  1. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  2. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  3. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  4. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  5. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  6. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  7. 2018Which Training Methods for GANs do actually Converge?cited by 679
  8. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  9. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  10. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  11. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  12. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
  13. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  14. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  15. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  16. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  17. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  18. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  19. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  20. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  21. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  22. 2020Improved Techniques for Training Single-Image GANscited by 78
  23. 2022GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifoldscited by 73
  24. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  25. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  26. 2020Deep Geometric Texture Synthesiscited by 51
  27. 2022Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesiscited by 43
  28. 2022Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Imagescited by 39
  29. 20223D-Aware Indoor Scene Synthesis with Depth Priorscited by 32
  30. 2022Learning to Generate 3D Shapes from a Single Examplecited by 31
  31. 2022GANimator: Neural Motion Synthesis from a Single Sequencecited by 23
  32. 2020GramGAN: Deep 3D Texture Synthesis From 2D Exemplarscited by 18
  33. 20223D-Aware Video Generationcited by 17
  34. 2021Diverse Generation from a Single Video Made Possiblecited by 13
  35. 2022SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scenecited by 8

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 2; 2025: 3.

11 papers.

  1. 2023Single Motion Diffusioncited by 65
  2. 2023CC3D: Layout-Conditioned Generation of Compositional 3D Scenescited by 58
  3. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shapecited by 29
  4. 2023GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fieldscited by 26
  5. 2023Efficient 3D Articulated Human Generation with Layered Surface Volumescited by 13
  6. 2025ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusioncited by 3
  7. 2024Prim2Room: Layout-Controllable Room Mesh Generation from Primitivescited by 2
  8. 2023GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learningcited by 1
  9. 2024Towards Practical Single-shot Motion Synthesiscited by 1
  10. 2025Controllable Single-shot Animation Blending with Temporal Conditioningcited by 1
  11. 2025LPA3D: 3D Room-Level Scene Generation from In-the-Wild Imagescited by 0