mlsanityData to 14 Oct 2026

StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis

arXiv 2110.08985 ↗First posted 18 Oct 2021cs.CV stat.MLcited by 477

Not on the map. Why?

Cited by 70 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose StyleNeRF, a 3D-aware generative model for photo-realistic high-resolution image synthesis with high multi-view consistency, which can be trained on unstructured 2D images. Existing approaches either cannot synthesize high-resolution images with fine details or yield noticeable 3D-inconsistent artifacts. In addition, many of them lack control over style attributes and explicit 3D camera poses. StyleNeRF integrates the neural radiance field (NeRF) into a style-based generator to tackle the aforementioned challenges, i.e., improving rendering efficiency and 3D consistency for high-resolution image generation. We perform volume rendering only to produce a low-resolution feature map and progressively apply upsampling in 2D to address the first issue. To mitigate the inconsistencies caused by 2D upsampling, we propose multiple designs, including a better upsampler and a new regularization loss. With these designs, StyleNeRF can synthesize high-resolution images at interactive rates while preserving 3D consistency at high quality. StyleNeRF also enables control of camera poses and different levels of styles, which can generalize to unseen views. It also supports challenging tasks, including zoom-in and-out, style mixing, inversion, and semantic editing.

Key facts. Cited by 477 papers in the map (data through 14 Oct 2026). Builds on 44 of its 54 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

44 of 54 references.

References · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  10. 2018Demystifying MMD GANscited by 1,293
  11. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
32 more
  1. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  2. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  3. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  4. 2020Neural Sparse Voxel Fieldscited by 959
  5. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  6. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  9. 2020Convolutional Occupancy Networkscited by 761
  10. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  11. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  12. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  13. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  14. 2018Which Training Methods for GANs do actually Converge?cited by 679
  15. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
  16. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  17. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
  18. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  19. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 268
  20. 2019The Deepfake Detection Challenge (DFDC) Preview Datasetcited by 209
  21. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  22. 2020BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Imagescited by 166
  23. 2015A Large-Scale Car Dataset for Fine-Grained Categorization and Verificationcited by 130
  24. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  25. 2021GAN-Control: Explicitly Controllable GANscited by 91
  26. 2020SofGAN: A Portrait Image Generator with Dynamic Stylingcited by 65
  27. 2016Generative Multi-Adversarial Networkscited by 60
  28. 2019HoloGAN: Unsupervised learning of 3D representations from natural imagescited by 59
  29. 2021CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fieldscited by 55
  30. 2020PIE: Portrait Image Embedding for Semantic Controlcited by 41
  31. 2018Dropout-GAN: Learning from a Dynamic Ensemble of Discriminatorscited by 15
  32. 2018On-line Adaptative Curriculum Learning for GANscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 124; 2023: 187; 2024: 95; 2025: 37; 2026: 14.

477 papers.

Sort:

By area:

  1. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  2. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  3. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  4. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  5. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 699
  6. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  7. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  8. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  9. 2021Neural Fields in Visual Computing and Beyondcited by 540
  10. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  11. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  12. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
38 more
  1. 2021Advances in Neural Renderingcited by 365
  2. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  3. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  4. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  5. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  6. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  7. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  8. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  9. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 274
  10. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 250
  11. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 235
  12. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  13. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  14. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  15. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  16. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  17. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  18. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  19. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 180
  20. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  21. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  22. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  23. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 158
  24. 2023WonderJourney: Going from Anywhere to Everywherecited by 158
  25. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  26. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 152
  27. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  28. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  29. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  30. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 144
  31. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 139
  32. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  33. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  34. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  35. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  36. 2021FENeRF: Face Editing in Neural Radiance Fieldscited by 112
  37. 2022EfficientNeRF: Efficient Neural Radiance Fieldscited by 111
  38. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111

50 most cited of 477 All 477 (JSON)