mlsanityData to 7 Oct 2026

GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields

arXiv 2011.12100 ↗First posted 24 Nov 2020cs.CV cs.LGcited by 784

Not on the map. Why?

Cited by 96 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle underlying factors of variation in the data, most of them operate in 2D and hence ignore that our world is three-dimensional. Further, only few works consider the compositional nature of scenes. Our key hypothesis is that incorporating a compositional 3D scene representation into the generative model leads to more controllable image synthesis. Representing scenes as compositional generative neural feature fields allows us to disentangle one or multiple objects from the background as well as individual objects' shapes and appearances while learning from unstructured and unposed image collections without any additional supervision. Combining this scene representation with a neural rendering pipeline yields a fast and realistic image synthesis model. As evidenced by our experiments, our model is able to disentangle individual objects and allows for translating and rotating them in the scene as well as changing the camera pose.

Key facts. Cited by 784 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 81; 2022: 207; 2023: 262; 2024: 151; 2025: 56; 2026: 27.

784 papers.

Sort:

By area:

  1. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  4. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  5. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  6. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  7. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  8. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  9. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  10. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  11. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  12. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
38 more
  1. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  2. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  3. 2021Neural Fields in Visual Computing and Beyondcited by 539
  4. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  5. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  6. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  7. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  8. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  9. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  10. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  11. 2021Advances in Neural Renderingcited by 365
  12. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  13. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  14. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  15. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  16. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  17. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
  18. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  19. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  20. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  21. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  22. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  23. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  24. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  25. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  26. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  27. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  28. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  29. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  30. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  31. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  32. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  33. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  34. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 195
  35. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  36. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  37. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  38. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180

50 most cited of 784 All 784 (JSON)