mlsanityData to 7 Oct 2026

Efficient Geometry-aware 3D Generative Adversarial Networks

arXiv 2112.07945 ↗First posted 15 Dec 2021cs.CV cs.AI cs.GRcited by 1,204

Not on the map. Why?

Cited by 218 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations that are not 3D-consistent; the former limits quality and resolution of the generated images and the latter adversely affects multi-view consistency and shape quality. In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations. We introduce an expressive hybrid explicit-implicit network architecture that, together with other design choices, synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry. By decoupling feature generation and neural rendering, our framework is able to leverage state-of-the-art 2D CNN generators, such as StyleGAN2, and inherit their efficiency and expressiveness. We demonstrate state-of-the-art 3D-aware synthesis with FFHQ and AFHQ Cats, among other experiments.

Key facts. Cited by 1,204 papers in the map (data through 7 Oct 2026). Builds on 67 of its 87 references that are in the map. First posted on arXiv 15 Dec 2021.

Builds on

67 of 87 references.

References · 67

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  11. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  12. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
38 more
  1. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  2. 2018Demystifying MMD GANscited by 1,268
  3. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  4. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  5. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  6. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  11. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  12. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  13. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  14. 2020Convolutional Occupancy Networkscited by 760
  15. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  16. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  17. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  18. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  19. 2018Which Training Methods for GANs do actually Converge?cited by 672
  20. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  21. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  22. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  23. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  24. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  25. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  26. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
  27. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  28. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  29. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  30. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  31. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  32. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  33. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  34. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  35. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  36. 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
  37. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  38. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 138; 2023: 411; 2024: 352; 2025: 197; 2026: 103.

1,204 papers.

Sort:

By area:

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  3. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  4. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  5. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  6. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  7. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  8. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  9. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  10. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  11. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  12. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
38 more
  1. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  2. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  3. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  4. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  5. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  6. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  7. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  8. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  9. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  10. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  11. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  12. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  13. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  14. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  15. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  16. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  17. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  18. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  19. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  20. 2022Novel View Synthesis with Diffusion Modelscited by 299
  21. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  22. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
  23. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  24. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  25. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  26. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  27. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  28. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  29. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  30. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  31. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
  32. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  33. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  34. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  35. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  36. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  37. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 220
  38. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218

50 most cited of 1,204 All 1,204 (JSON)