mlsanityData to 7 Oct 2026

MegaPortraits: One-shot Megapixel Neural Head Avatars

arXiv 2207.07621 ↗First posted 15 Jul 2022cs.CVcited by 131

Not on the map. Why?

Cited by 23 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work, we advance the neural head avatar technology to the megapixel resolution while focusing on the particularly challenging task of cross-driving synthesis, i.e., when the appearance of the driving image is substantially different from the animated source image. We propose a set of new neural architectures and training methods that can leverage both medium-resolution video data and high-resolution image data to achieve the desired levels of rendered image quality and generalization to novel views and motion. We demonstrate that suggested architectures and methods produce convincing high-resolution neural avatars, outperforming the competitors in the cross-driving scenario. Lastly, we show how a trained high-resolution neural avatar model can be distilled into a lightweight student model which runs in real-time and locks the identities of neural avatars to several dozens of pre-defined source images. Real-time operation and identity lock are essential for many practical applications head avatar systems.

Key facts. Cited by 131 papers in the map (data through 7 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 15 Jul 2022.

Builds on

29 of 46 references.

References · 29

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  5. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  6. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  7. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  8. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  9. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  10. 2020First Order Motion Model for Image Animationcited by 698
  11. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  12. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
17 more
  1. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  2. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 438
  3. 2018Video-to-Video Synthesiscited by 388
  4. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  5. 2018Deep Video Portraitscited by 265
  6. 2018Animating Arbitrary Objects via Deep Motion Transfercited by 206
  7. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  8. 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
  9. 2018Deep Appearance Models for Face Renderingcited by 164
  10. 2017S3FD: Single Shot Scale-invariant Face Detectorcited by 142
  11. 2020MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decompositioncited by 127
  12. 2020Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatarscited by 116
  13. 2020Neural Head Reenactment with Latent Pose Descriptorscited by 106
  14. 2020HeadGAN: One-shot Neural Head Synthesis and Editingcited by 105
  15. 2019MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targetscited by 90
  16. 2019Graphonomy: Universal Human Parsing via Graph Transfer Learningcited by 81
  17. 2020HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishmentcited by 70

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 29; 2024: 39; 2025: 39; 2026: 17.

131 papers.

Sort:

By area:

  1. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  2. 2024LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Controlcited by 202
  3. 2024Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animationcited by 198
  4. 2024EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditionscited by 196
  5. 2024VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Timecited by 186
  6. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 172
  7. 2024Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependencycited by 102
  8. 2024Generalizable and Animatable Gaussian Head Avatarcited by 95
  9. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  10. 2024X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attentioncited by 88
  11. 2024GPAvatar: Generalizable and Precise Head Avatar from Image(s)cited by 74
  12. 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
38 more
  1. 2022MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptationcited by 69
  2. 2023One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Fieldcited by 68
  3. 2024EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatarscited by 65
  4. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  5. 2024Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizercited by 64
  6. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited by 55
  7. 2025HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animationcited by 55
  8. 2023NOFA: NeRF-based One-shot Facial Avatar Reconstructioncited by 53
  9. 2023StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Videocited by 52
  10. 2024CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Modelscited by 52
  11. 2025Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatarscited by 52
  12. 2023LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatarcited by 50
  13. 2023DPE: Disentanglement of Pose and Expression for General Video Portrait Editingcited by 45
  14. 2024HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priorscited by 44
  15. 2023GAIA: Zero-shot Talking Avatar Generationcited by 43
  16. 2025LAM: Large Avatar Model for One-shot Animatable Gaussian Headcited by 43
  17. 2024Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesiscited by 41
  18. 2025Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animationcited by 41
  19. 2024FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portraitcited by 40
  20. 2024INFP: Audio-Driven Interactive Head Generation in Dyadic Conversationscited by 40
  21. 2025DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidancecited by 36
  22. 2023VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactmentcited by 33
  23. 2024MegActor: Harness the Power of Raw Video for Vivid Portrait Animationcited by 27
  24. 2025X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attentioncited by 26
  25. 2023CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformercited by 24
  26. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  27. 2023Generalizable One-shot Neural Head Avatarcited by 21
  28. 2025Pippo: High-Resolution Multi-View Humans from a Single Imagecited by 20
  29. 2022DINER: Depth-aware Image-based NEural Radiance fieldscited by 19
  30. 2023InvertAvatar: Incremental GAN Inversion for Generalized Head Avatarscited by 19
  31. 2024VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresencecited by 19
  32. 2023Unsupervised Volumetric Animationcited by 18
  33. 2025MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generationcited by 18
  34. 2024Joker: Conditional 3D Head Synthesis with Extreme Facial Expressionscited by 17
  35. 2025MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatarscited by 17
  36. 2026Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversationcited by 17
  37. 2025Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generationcited by 16
  38. 2025CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulationcited by 16

50 most cited of 131 All 131 (JSON)