mlsanityData to 7 Oct 2026

FENeRF: Face Editing in Neural Radiance Fields

arXiv 2111.15490 ↗First posted 30 Nov 2021cs.CVcited by 112

Not on the map. Why?

Abstract (arXiv)

Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency. 3D-aware GAN methods can maintain view consistency but their generated images are not locally editable. To overcome these limitations, we propose FENeRF, a 3D-aware generator that can produce view-consistent and locally-editable portrait images. Our method uses two decoupled latent codes to generate corresponding facial semantics and texture in a spatial aligned 3D volume with shared geometry. Benefiting from such underlying 3D representation, FENeRF can jointly render the boundary-aligned image and semantic mask and use the semantic mask to edit the 3D volume via GAN inversion. We further show such 3D representation can be learned from widely available monocular image and semantic mask pairs. Moreover, we reveal that joint learning semantics and texture helps to generate finer geometry. Our experiments demonstrate that FENeRF outperforms state-of-the-art methods in various face editing tasks.

Key facts. Cited by 112 papers in the map (data through 7 Oct 2026). Builds on 47 of its 55 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

47 of 55 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  10. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  12. 2018Demystifying MMD GANscited by 1,268
35 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  2. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  3. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  4. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  5. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  6. 2018Which Training Methods for GANs do actually Converge?cited by 672
  7. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  8. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  9. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  10. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  11. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  12. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  13. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  14. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  15. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  16. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  17. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  18. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  19. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 302
  20. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 267
  21. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  22. 2021Editing Conditional Radiance Fieldscited by 222
  23. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  24. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  25. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  26. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  27. 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124
  28. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  29. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  30. 2018MaskGAN: Better Text Generation via Filling in the______cited by 89
  31. 2020SofGAN: A Portrait Image Generator with Dynamic Stylingcited by 65
  32. 2020Deep Generation of Face Images from Sketchescited by 32
  33. 2021Differentiable Surface Rendering via Non-Differentiable Samplingcited by 28
  34. 2020DeepFacePencil: Creating Face Images from Freehand Sketchescited by 19
  35. 2021FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifoldcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 33; 2023: 40; 2024: 23; 2025: 9; 2026: 5.

112 papers.

Sort:

By area:

  1. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  2. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 141
  3. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  4. 2022Generative Neural Articulated Radiance Fieldscited by 101
  5. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  6. 2023SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Fieldcited by 93
  7. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 91
  8. 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
  9. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  10. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  11. 2024Advances in 3D Generation: A Surveycited by 62
  12. 20223D GAN Inversion for Controllable Portrait Image Animationcited by 53
38 more
  1. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  2. 2023PIE-NeRF: Physics-based Interactive Elastodynamics with NeRFcited by 51
  3. 2023LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatarcited by 50
  4. 2022UV Volumes for Real-time Rendering of Editable Free-view Human Performancecited by 43
  5. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 43
  6. 2022FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editingcited by 38
  7. 2023ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Imagescited by 38
  8. 2022Controllable 3D Face Synthesis with Conditional Generative Occupancy Fieldscited by 37
  9. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  10. 2022NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fieldscited by 33
  11. 20213D-Aware Semantic-Guided Generative Model for Human Synthesiscited by 31
  12. 2022EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Pointscited by 30
  13. 2024SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representationcited by 30
  14. 2022Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fieldscited by 29
  15. 2022High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priorscited by 28
  16. 2023BeyondPixels: A Comprehensive Review of the Evolution of Neural Radiance Fieldscited by 27
  17. 2023UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fieldscited by 26
  18. 20233D-aware Conditional Image Synthesiscited by 24
  19. 20223DFaceShop: Explicitly Controllable 3D-Aware Portrait Generationcited by 22
  20. 2023LPFF: A Portrait Dataset for Face Generators Across Large Posescited by 22
  21. 2024Mani-GS: Gaussian Splatting Manipulation with Triangular Meshcited by 22
  22. 2023Local 3D Editing via 3D Distillation of CLIP Knowledgecited by 20
  23. 2022Neural Parameterization for Dynamic Human Head Editingcited by 16
  24. 2022GAN-based Facial Attribute Manipulationcited by 16
  25. 2022A Survey on Deep Generative 3D-aware Image Synthesiscited by 16
  26. 2024Tri2-plane: Thinking Head Avatar via Feature Pyramidcited by 16
  27. 202415M Multimodal Facial Image-Text Datasetcited by 14
  28. 2025Simulating the Real World: A Unified Survey of Multimodal Generative Modelscited by 14
  29. 2023Efficient 3D Articulated Human Generation with Layered Surface Volumescited by 13
  30. 2023FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fieldscited by 12
  31. 2023Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Imagescited by 12
  32. 2023ReliTalk: Relightable Talking Portrait Generation from a Single Videocited by 12
  33. 2022Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesiscited by 11
  34. 2023USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fieldscited by 11
  35. 2022NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimationcited by 10
  36. 2023Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Fieldcited by 10
  37. 2023Frequency-Modulated Point Cloud Rendering with Easy Editingcited by 10
  38. 2024Real-time 3D-aware Portrait Editing from a Single Imagecited by 10

50 most cited of 112 All 112 (JSON)