{"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/riggable-3d-face-reconstruction-via-in","title":"Riggable 3D Face Reconstruction via In-Network Optimization","arxiv_id":"2104.03493","date":"2021-04-08","proceeding":"CVPR 2021 1","authors":["Ziqian Bai","Zhaopeng Cui","Xiaoming Liu","Ping Tan"],"abstract":"This paper presents a method for riggable 3D face reconstruction from monocular images, which jointly estimates a personalized face rig and per-image parameters including expressions, poses, and illuminations. To achieve this goal, we design an end-to-end trainable network embedded with a differentiable in-network optimization. The network first parameterizes the face rig as a compact latent code with a neural decoder, and then estimates the latent code as well as per-image parameters via a learnable optimization. By estimating a personalized face rig, our method goes beyond static reconstructions and enables downstream applications such as video retargeting. In-network optimization explicitly enforces constraints derived from the first principles, thus introduces additional priors than regression-based methods. Finally, data-driven priors from deep learning are utilized to constrain the ill-posed monocular setting and ease the optimization difficulty. Experiments demonstrate that our method achieves SOTA reconstruction accuracy, reasonable robustness and generalization ability, and supports standard face rig applications.","url_abs":"https://arxiv.org/abs/2104.03493v1","url_pdf":"https://arxiv.org/pdf/2104.03493v1.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":"riggable-3d-face-reconstruction-via-in","repo_url":"https://github.com/zqbai-jeremy/INORig","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-face-reconstruction","task_name":"3D Face Reconstruction"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"face-reconstruction","task_name":"Face Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.03493","atlas_url":"https://app.syntology.ai/?focus=2104.03493","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}