{"pk":30043,"title":"Learning a Generative Model of Human Faces Through Inverse Rendering","subtitle":null,"abstract":"Generative models in an inverse graphics framework are appealing models for visual perception. How might childrenacquire them? We present a computational procedure for learning generative models of human faces using developmen-tally plausible input. Our statistical model of shape and appearance initially uses the average face as a template with asimple Gaussian process model of deformations. We iteratively learn the statistical distribution of faces by performinganalysis-by-synthesis on a small number of images and combine the results to construct an improved generative model.Our analysis-by-synthesis framework combines a convolutional neural network for fast inference with a Markov chainMonte Carlo process for detailed refinement. This learning strategy quickly captures the variation of natural faces anddemonstrates an efficient way to learn the distribution of faces.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Poster Session 3","is_remote":true,"remote_url":"https://escholarship.org/uc/item/91k0t5pc","frozenauthors":[{"first_name":"Skylar","middle_name":"","last_name":"Sutherland","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""},{"first_name":"Bernhard","middle_name":"","last_name":"Egger","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""},{"first_name":"Josh","middle_name":"","last_name":"Tenenbaum","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2020-01-02T02:00:00+08:00","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/30043/galley/19897/download/"}]}