{"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/fast-bi-layer-neural-synthesis-of-one-shot","title":"Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars","arxiv_id":"2008.10174","date":"2020-08-24","proceeding":"ECCV 2020 8","authors":["Egor Zakharov","Aleksei Ivakhnenko","Aliaksandra Shysheya","Victor Lempitsky"],"abstract":"We propose a neural rendering-based system that creates head avatars from a single photograph. Our approach models a person's appearance by decomposing it into two layers. The first layer is a pose-dependent coarse image that is synthesized by a small neural network. The second layer is defined by a pose-independent texture image that contains high-frequency details. The texture image is generated offline, warped and added to the coarse image to ensure a high effective resolution of synthesized head views. We compare our system to analogous state-of-the-art systems in terms of visual quality and speed. The experiments show significant inference speedup over previous neural head avatar models for a given visual quality. We also report on a real-time smartphone-based implementation of our system.","url_abs":"https://arxiv.org/abs/2008.10174v1","url_pdf":"https://arxiv.org/pdf/2008.10174v1.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":"fast-bi-layer-neural-synthesis-of-one-shot","repo_url":"https://github.com/saic-violet/bilayer-model","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MPL-2.0"}}],"tasks":[{"task_slug":"neural-rendering","task_name":"Neural Rendering"},{"task_slug":"talking-head-generation","task_name":"Talking Head Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-1-shot","task":"Talking Head Generation","dataset":"VoxCeleb2 - 1-shot learning","model":"Fast Bi-layer Avatars (medium size)","rank_in_archive_order":1,"of":5,"metrics":{"CSIM":"0.653","LPIPS":"0.358","Normalized Pose Error":"43.3","SSIM":"0.508","inference time (ms)":"4"},"uses_additional_data":false},{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-1-shot","task":"Talking Head Generation","dataset":"VoxCeleb2 - 1-shot learning","model":"First Order Motion Model (medium size)","rank_in_archive_order":2,"of":5,"metrics":{"CSIM":"0.638","LPIPS":"0.311","Normalized Pose Error":"47.8","SSIM":"0.553","inference time (ms)":"13"},"uses_additional_data":false},{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-1-shot","task":"Talking Head Generation","dataset":"VoxCeleb2 - 1-shot learning","model":"Few-shot Vid-to-vid (medium size)","rank_in_archive_order":3,"of":5,"metrics":{"CSIM":"0.604","LPIPS":"0.368","Normalized Pose Error":"46.1","SSIM":"0.419","inference time (ms)":"22"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.10174","atlas_url":"https://app.syntology.ai/?focus=2008.10174","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}