{"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/combining-3d-morphable-models-a-large-scale","title":"Combining 3D Morphable Models: A Large scale Face-and-Head Model","arxiv_id":"1903.03785","date":"2019-03-09","proceeding":"CVPR 2019 6","authors":["Stylianos Ploumpis","Haoyang Wang","Nick Pears","William A. P. Smith","Stefanos Zafeiriou"],"abstract":"Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for\nrepresenting the 3D surfaces of an object class. In this context, we identify\nan interesting question that has previously not received research attention: is\nit possible to combine two or more 3DMMs that (a) are built using different\ntemplates that perhaps only partly overlap, (b) have different representation\ncapabilities and (c) are built from different datasets that may not be\npublicly-available? In answering this question, we make two contributions.\nFirst, we propose two methods for solving this problem: i. use a regressor to\ncomplete missing parts of one model using the other, ii. use the Gaussian\nProcess framework to blend covariance matrices from multiple models. Second, as\nan example application of our approach, we build a new face-and-head shape\nmodel that combines the variability and facial detail of the LSFM with the full\nhead modelling of the LYHM. The resulting combined shape model achieves\nstate-of-the-art performance and outperforms existing head models by a large\nmargin. Finally, as an application experiment, we reconstruct full head\nrepresentations from single, unconstrained images by utilizing our proposed\nlarge-scale model in conjunction with the FaceWarehouse blendshapes for\nhandling expressions.","url_abs":"http://arxiv.org/abs/1903.03785v1","url_pdf":"http://arxiv.org/pdf/1903.03785v1.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":"combining-3d-morphable-models-a-large-scale","repo_url":"https://github.com/nabeel3133/combining3dmorphablemodels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.03785","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}