mlsanityData to 14 Oct 2026

DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis

arXiv 2503.15667 ↗First posted 19 Mar 2025cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Generating high-quality 360-degree views of human heads from single-view images is essential for enabling accessible immersive telepresence applications and scalable personalized content creation. While cutting-edge methods for full head generation are limited to modeling realistic human heads, the latest diffusion-based approaches for style-omniscient head synthesis can produce only frontal views and struggle with view consistency, preventing their conversion into true 3D models for rendering from arbitrary angles. We introduce a novel approach that generates fully consistent 360-degree head views, accommodating human, stylized, and anthropomorphic forms, including accessories like glasses and hats. Our method builds on the DiffPortrait3D framework, incorporating a custom ControlNet for back-of-head detail generation and a dual appearance module to ensure global front-back consistency. By training on continuous view sequences and integrating a back reference image, our approach achieves robust, locally continuous view synthesis. Our model can be used to produce high-quality neural radiance fields (NeRFs) for real-time, free-viewpoint rendering, outperforming state-of-the-art methods in object synthesis and 360-degree head generation for very challenging input portraits.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 45 of its 61 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

45 of 61 references.

References · 45

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  8. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  9. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  11. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  12. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
33 more
  1. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  2. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  3. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  4. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  5. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  6. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  7. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  8. 2020State of the Art on Neural Renderingcited by 278
  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. 2023NeRSemble: Multi-view Radiance Field Reconstruction of Human Headscited by 194
  12. 2018Deep Appearance Models for Face Renderingcited by 164
  13. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 135
  14. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  15. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  16. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  17. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  18. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  19. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  20. 2023Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priorscited by 64
  21. 2024Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizercited by 64
  22. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited by 55
  23. 2021Generative Occupancy Fields for 3D Surface-Aware Image Synthesiscited by 51
  24. 2021Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracingcited by 48
  25. 2019MVF-Net: Multi-View 3D Face Morphable Model Regressioncited by 45
  26. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  27. 2021Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinementcited by 36
  28. 2023VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactmentcited by 33
  29. 2024SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representationcited by 30
  30. 2023DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesiscited by 26
  31. 2024VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresencecited by 19
  32. 2024Joker: Conditional 3D Head Synthesis with Extreme Facial Expressionscited by 18
  33. 2022Novel View Synthesis for High-fidelity Headshot Scenescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 7.

12 papers.

  1. 2025SOAP: Style-Omniscient Animatable Portraitscited by 11
  2. 2026FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animationcited by 4
  3. 2025SpinMeRound: Consistent Multi-View Identity Generation Using Diffusion Modelscited by 3
  4. 2025Stable-Hair v2: Real-World Hair Transfer via Multiple-View Diffusion Modelcited by 2
  5. 2026Condition Matters in Full-head 3D GANscited by 2
  6. 2026Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Imagecited by 1
  7. 2026Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generationcited by 1
  8. 2025StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulationcited by 0
  9. 2025Envision: Embodied Visual Planning via Goal-Imagery Video Diffusioncited by 0
  10. 2026You Only Need One Stage: Novel-View Synthesis From A Single Blind Face Imagecited by 0
  11. 2026Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatarscited by 0
  12. 2026GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusioncited by 0