mlsanityData to 14 Oct 2026

SpinMeRound: Consistent Multi-View Identity Generation Using Diffusion Models

arXiv 2504.10716 ↗First posted 14 Apr 2025cs.CVcited by 3

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Despite recent progress in diffusion models, generating realistic head portraits from novel viewpoints remains a significant challenge. Most current approaches are constrained to limited angular ranges, predominantly focusing on frontal or near-frontal views. Moreover, although the recent emerging large-scale diffusion models have been proven robust in handling 3D scenes, they underperform on facial data, given their complex structure and the uncanny valley pitfalls. In this paper, we propose SpinMeRound, a diffusion-based approach designed to generate consistent and accurate head portraits from novel viewpoints. By leveraging a number of input views alongside an identity embedding, our method effectively synthesizes diverse viewpoints of a subject whilst robustly maintaining its unique identity features. Through experimentation, we showcase our model's generation capabilities in 360 head synthesis, while beating current state-of-the-art multiview diffusion models.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 66 of its 78 references that are in the map. First posted on arXiv 14 Apr 2025.

Builds on

66 of 78 references.

References · 66

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  11. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
38 more
  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  2. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  3. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  4. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  5. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  6. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  7. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  8. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  9. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  10. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 436
  11. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  12. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  13. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  14. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  15. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  16. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  17. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 255
  18. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  19. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 227
  20. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 223
  21. 2023NeRSemble: Multi-view Radiance Field Reconstruction of Human Headscited by 194
  22. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  23. 2020i3DMM: Deep Implicit 3D Morphable Model of Human Headscited by 109
  24. 2024Arc2Face: A Foundation Model for ID-Consistent Human Facescited by 101
  25. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 100
  26. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  27. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 89
  28. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesiscited by 84
  29. 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generationcited by 84
  30. 2022Learning Neural Parametric Head Modelscited by 73
  31. 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
  32. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  33. 2024Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizercited by 64
  34. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited by 55
  35. 2024CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Modelscited by 52
  36. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  37. 2023FitMe: Deep Photorealistic 3D Morphable Model Avatarscited by 38
  38. 2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 36

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generationcited by 1
  2. 2026HumanOrbit: 3D Human Reconstruction as 360deg Orbit Generationcited by 0
  3. 2026GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TurboPortrait3D: Single-step diffusion-based fast portrait novel-view synthesis
  2. 2026ExpPortrait: Expressive Portrait Generation via Personalized Representation
  3. 2023Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation
  4. 2024Human Multi-View Synthesis from a Single-View Model:Transferred Body and Face Representations
  5. 2024DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis
  6. 2024Identity Preserving 3D Head Stylization with Multiview Score Distillation
  7. 2024VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis
  8. 2025Joint Learning of Depth and Appearance for Portrait Image Animation