DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gu, Yuming, Tran, Phong, Zheng, Yujian, Xu, Hongyi, Li, Heyuan, Karmanov, Adilbek, Li, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909545084747776
author Gu, Yuming
Tran, Phong
Zheng, Yujian
Xu, Hongyi
Li, Heyuan
Karmanov, Adilbek
Li, Hao
author_facet Gu, Yuming
Tran, Phong
Zheng, Yujian
Xu, Hongyi
Li, Heyuan
Karmanov, Adilbek
Li, Hao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15667
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis
Gu, Yuming
Tran, Phong
Zheng, Yujian
Xu, Hongyi
Li, Heyuan
Karmanov, Adilbek
Li, Hao
Computer Vision and Pattern Recognition
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.
title DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.15667