{"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/morphable-face-models-an-open-framework","title":"Morphable Face Models - An Open Framework","arxiv_id":"1709.08398","date":"2017-09-25","proceeding":null,"authors":["Thomas Gerig","Andreas Morel-Forster","Clemens Blumer","Bernhard Egger","Marcel Lüthi","Sandro Schönborn","Thomas Vetter"],"abstract":"In this paper, we present a novel open-source pipeline for face registration\nbased on Gaussian processes as well as an application to face image analysis.\nNon-rigid registration of faces is significant for many applications in\ncomputer vision, such as the construction of 3D Morphable face models (3DMMs).\nGaussian Process Morphable Models (GPMMs) unify a variety of non-rigid\ndeformation models with B-splines and PCA models as examples. GPMM separate\nproblem specific requirements from the registration algorithm by incorporating\ndomain-specific adaptions as a prior model. The novelties of this paper are the\nfollowing: (i) We present a strategy and modeling technique for face\nregistration that considers symmetry, multi-scale and spatially-varying\ndetails. The registration is applied to neutral faces and facial expressions.\n(ii) We release an open-source software framework for registration and\nmodel-building, demonstrated on the publicly available BU3D-FE database. The\nreleased pipeline also contains an implementation of an Analysis-by-Synthesis\nmodel adaption of 2D face images, tested on the Multi-PIE and LFW database.\nThis enables the community to reproduce, evaluate and compare the individual\nsteps of registration to model-building and 3D/2D model fitting. (iii) Along\nwith the framework release, we publish a new version of the Basel Face Model\n(BFM-2017) with an improved age distribution and an additional facial\nexpression model.","url_abs":"http://arxiv.org/abs/1709.08398v2","url_pdf":"http://arxiv.org/pdf/1709.08398v2.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":"morphable-face-models-an-open-framework","repo_url":"https://github.com/unibas-gravis/basel-face-pipeline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"morphable-face-models-an-open-framework","repo_url":"https://github.com/unibas-gravis/parametric-face-image-generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"face-model","task_name":"Face Model"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.08398","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}