DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis
Gu, Yuming Tran, Phong Zheng, Yujian Xu, Hongyi Li, Heyuan Karmanov, Adilbek Li, Hao
Gu, Yuming
Tran, Phong
Zheng, Yujian
Xu, Hongyi
Li, Heyuan
Karmanov, Adilbek
Li, Hao
Author
Gu, Yuming, Tran, Phong, Zheng, Yujian, Xu, Hongyi, Li, Heyuan, Karmanov, Adilbek, Li, Hao
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
An error occurred retrieving the object's statistics
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
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 DiffPor-trait3D 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.
Citation
Y. Gu et al., "DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis," 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2025, pp. 26263-26273, doi: 10.1109/CVPR52734.2025.02446.
Source
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Conference
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025
Keywords
Diffusion Models, Human Head, Novel View Synthesis
Subjects
Source
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025
Publisher
IEEE