{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-full-head-3d-gans-from-a-single-view","title":"3DPortraitGAN: Learning One-Quarter Headshot 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses","arxiv_id":"2307.14770","date":"2023-07-27","proceeding":null,"authors":["Yiqian Wu","Hao Xu","Xiangjun Tang","Hongbo Fu","Xiaogang Jin"],"abstract":"3D-aware face generators are typically trained on 2D real-life face image datasets that primarily consist of near-frontal face data, and as such, they are unable to construct one-quarter headshot 3D portraits with complete head, neck, and shoulder geometry. Two reasons account for this issue: First, existing facial recognition methods struggle with extracting facial data captured from large camera angles or back views. Second, it is challenging to learn a distribution of 3D portraits covering the one-quarter headshot region from single-view data due to significant geometric deformation caused by diverse body poses. To this end, we first create the dataset 360{\\deg}-Portrait-HQ (360{\\deg}PHQ for short) which consists of high-quality single-view real portraits annotated with a variety of camera parameters (the yaw angles span the entire 360{\\deg} range) and body poses. We then propose 3DPortraitGAN, the first 3D-aware one-quarter headshot portrait generator that learns a canonical 3D avatar distribution from the 360{\\deg}PHQ dataset with body pose self-learning. Our model can generate view-consistent portrait images from all camera angles with a canonical one-quarter headshot 3D representation. Our experiments show that the proposed framework can accurately predict portrait body poses and generate view-consistent, realistic portrait images with complete geometry from all camera angles.","url_abs":"https://arxiv.org/abs/2307.14770v2","url_pdf":"https://arxiv.org/pdf/2307.14770v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-full-head-3d-gans-from-a-single-view","repo_url":"https://github.com/oneThousand1000/3DPortraitGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"self-learning","task_name":"Self-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.14770","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}