mlsanityData to 14 Oct 2026

Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360deg

arXiv 2408.00296 ↗First posted 1 Aug 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Creating a 360deg parametric model of a human head is a very challenging task. While recent advancements have demonstrated the efficacy of leveraging synthetic data for building such parametric head models, their performance remains inadequate in crucial areas such as expression-driven animation, hairstyle editing, and text-based modifications. In this paper, we build a dataset of artist-designed high-fidelity human heads and propose to create a novel parametric 360deg renderable parametric head model from it. Our scheme decouples the facial motion/shape and facial appearance, which are represented by a classic parametric 3D mesh model and an attached neural texture, respectively. We further propose a training method for decompositing hairstyle and facial appearance, allowing free-swapping of the hairstyle. A novel inversion fitting method is presented based on single image input with high generalization and fidelity. To the best of our knowledge, our model is the first parametric 3D full-head that achieves 360deg free-view synthesis, image-based fitting, appearance editing, and animation within a single model. Experiments show that facial motions and appearances are well disentangled in the parametric space, leading to SOTA performance in rendering and animating quality. The code and SynHead100 dataset are released at https://nju-3dv.github.io/projects/Head360.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 46 of its 71 references that are in the map. First posted on arXiv 1 Aug 2024.

Builds on

46 of 71 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  8. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  9. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  10. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  11. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  12. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
34 more
  1. 2017Generative Adversarial Networks: An Overviewcited by 590
  2. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  3. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  4. 2021GAN Inversion: A Surveycited by 367
  5. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  6. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  7. 20193D Morphable Face Models -- Past, Present and Futurecited by 270
  8. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  9. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 220
  10. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  11. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  12. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  13. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  14. 2018Nonlinear 3D Face Morphable Modelcited by 157
  15. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 148
  16. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  17. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  18. 2023Collaborative Diffusion for Multi-Modal Face Generation and Editingcited by 116
  19. 2021FENeRF: Face Editing in Neural Radiance Fieldscited by 112
  20. 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
  21. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  22. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  23. 2017Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hzcited by 91
  24. 2019Towards High-fidelity Nonlinear 3D Face Morphable Modelcited by 91
  25. 2018On Learning 3D Face Morphable Model from In-the-wild Imagescited by 54
  26. 2019Disentangled Representation Learning for 3D Face Shapecited by 48
  27. 2023VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Priorcited by 47
  28. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  29. 2019MeshGAN: Non-linear 3D Morphable Models of Facescited by 39
  30. 2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 36
  31. 2023High-Fidelity 3D Face Generation from Natural Language Descriptionscited by 33
  32. 2022Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Functioncited by 14
  33. 2020JNR: Joint-based Neural Rig Representation for Compact 3D Face Modelingcited by 7
  34. 2022Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solutioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2024IDOL: Instant Photorealistic 3D Human Creation from a Single Imagecited by 55
  2. 2025PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Imagecited by 7
  3. 2025HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesiscited by 6
  4. 2024Towards Native Generative Model for 3D Head Avatarcited by 5
  5. 2025TeRA: Rethinking Text-guided Realistic 3D Avatar Generationcited by 5
  6. 2025EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Headcited by 1
  7. 2025ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Modelscited by 1
  8. 2026Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognitioncited by 1
  9. 2026ManifoldSplat: Language-Guided Semantic Shape Editing of 3D Gaussian Head Avatarscited by 0