mlsanityData to 7 Oct 2026

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis

arXiv 2212.11984 ↗First posted 22 Dec 2022cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it serves as an intuitive user control for scene editing. Based on such a prior, the proposed model spatially disentangles the whole scene into object-centric generative radiance fields by learning on only 2D images with the global-local discrimination. Our model obtains the generation fidelity and editing flexibility of individual objects while being able to efficiently compose objects and the background into a complete scene. We demonstrate state-of-the-art performance on many scene datasets, including the challenging Waymo outdoor dataset. Project page: https://snap-research.github.io/discoscene/

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 57 of its 76 references that are in the map. First posted on arXiv 22 Dec 2022.

Builds on

57 of 76 references.

References · 57

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  9. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  10. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  11. 2018Demystifying MMD GANscited by 1,268
  12. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
38 more
  1. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  2. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  3. 2020Neural Sparse Voxel Fieldscited by 959
  4. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  5. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  6. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  7. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  8. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  9. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  10. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  11. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  12. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  13. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  14. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  15. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  16. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 375
  17. 2018Image Generation from Scene Graphscited by 324
  18. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  19. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  20. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  21. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  22. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 228
  23. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  24. 2020BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Imagescited by 166
  25. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  26. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 130
  27. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  28. 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124
  29. 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 122
  30. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  31. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  32. 2019Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesiscited by 106
  33. 2020Object-Centric Neural Scene Renderingcited by 90
  34. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  35. 2020Generative Hierarchical Features from Synthesizing Imagescited by 83
  36. 2022Object-Compositional Neural Implicit Surfacescited by 74
  37. 2021A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesiscited by 72
  38. 2020Efficient Semantic Image Synthesis via Class-Adaptive Normalizationcited by 58

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 24; 2024: 22; 2025: 9; 2026: 6.

61 papers.

Sort:

By area:

  1. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  2. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  3. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  4. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  5. 2024GenAD: Generalized Predictive Model for Autonomous Drivingcited by 150
  6. 2023Compositional 3D Scene Generation using Locally Conditioned Diffusioncited by 101
  7. 2023Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenescited by 75
  8. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  9. 2023Gaussian Shell Maps for Efficient 3D Human Generationcited by 61
  10. 2023CC3D: Layout-Conditioned Generation of Compositional 3D Scenescited by 58
  11. 2023CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layoutcited by 57
  12. 2023SceneWiz3D: Towards Text-guided 3D Scene Compositioncited by 54
38 more
  1. 2023SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priorscited by 43
  2. 2024SceneTeller: Language-to-3D Scene Generationcited by 43
  3. 2024SceneCraft: Layout-Guided 3D Scene Generationcited by 40
  4. 20233DAvatarGAN: Bridging Domains for Personalized Editable Avatarscited by 38
  5. 2023ObjectSDF++: Improved Object-Compositional Neural Implicit Surfacescited by 38
  6. 2024Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generationcited by 33
  7. 2024Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Modelscited by 30
  8. 2024S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generationcited by 28
  9. 2023UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fieldscited by 26
  10. 20253D Scene Generation: A Surveycited by 24
  11. 2023Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Modelscited by 22
  12. 2024InterFusion: Text-Driven Generation of 3D Human-Object Interactioncited by 18
  13. 2025MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generationcited by 18
  14. 2023Learning 3D-aware Image Synthesis with Unknown Pose Distributioncited by 14
  15. 2024RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenescited by 14
  16. 2024Urban Scene Diffusion through Semantic Occupancy Mapcited by 14
  17. 2023Efficient 3D Articulated Human Generation with Layered Surface Volumescited by 13
  18. 2024Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embeddingcited by 13
  19. 2024Customizing Text-to-Image Diffusion with Object Viewpoint Controlcited by 13
  20. 2023RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generationcited by 12
  21. 2024Move Anything with Layered Scene Diffusioncited by 12
  22. 2023Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updatescited by 9
  23. 2024Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Reviewcited by 9
  24. 2024MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assetscited by 6
  25. 20246Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstructioncited by 5
  26. 2025LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Groundingcited by 5
  27. 2023BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generationcited by 4
  28. 2026FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flowcited by 4
  29. 2026GenAssets: Generating in-the-wild 3D Assets in Latent Spacecited by 4
  30. 2023Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Imagescited by 3
  31. 2023Generating Transferable Adversarial Simulation Scenarios for Self-Driving via Neural Renderingcited by 3
  32. 2023Animating Street Viewcited by 3
  33. 2025VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangementcited by 3
  34. 2024My Body My Choice: Human-Centric Full-Body Anonymizationcited by 2
  35. 2024MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Renderingcited by 2
  36. 2025DualNeRF: Text-Driven 3D Scene Editing via Dual-Field Representationcited by 2
  37. 2025Neural USD: An object-centric framework for iterative editing and controlcited by 2
  38. 2026Disentangled Representation Learning via Flow Matchingcited by 2

50 most cited of 61 All 61 (JSON)