{"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/shape-and-spatially-varying-reflectance","title":"Shape and Spatially-Varying Reflectance Estimation From Virtual Exemplars","arxiv_id":"1512.05278","date":"2015-12-16","proceeding":null,"authors":["Zhuo Hui","Aswin C. Sankaranarayanan"],"abstract":"This paper addresses the problem of estimating the shape of objects that\nexhibit spatially-varying reflectance. We assume that multiple images of the\nobject are obtained under a fixed view-point and varying illumination, i.e.,\nthe setting of photometric stereo. At the core of our techniques is the\nassumption that the BRDF at each pixel lies in the non-negative span of a known\nBRDF dictionary.This assumption enables a per-pixel surface normal and BRDF\nestimation framework that is computationally tractable and requires no\ninitialization in spite of the underlying problem being non-convex. Our\nestimation framework first solves for the surface normal at each pixel using a\nvariant of example-based photometric stereo. We design an efficient multi-scale\nsearch strategy for estimating the surface normal and subsequently, refine this\nestimate using a gradient descent procedure. Given the surface normal estimate,\nwe solve for the spatially-varying BRDF by constraining the BRDF at each pixel\nto be in the span of the BRDF dictionary, here, we use additional priors to\nfurther regularize the solution. A hallmark of our approach is that it does not\nrequire iterative optimization techniques nor the need for careful\ninitialization, both of which are endemic to most state-of-the-art techniques.\nWe showcase the performance of our technique on a wide range of simulated and\nreal scenes where we outperform competing methods.","url_abs":"http://arxiv.org/abs/1512.05278v3","url_pdf":"http://arxiv.org/pdf/1512.05278v3.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":"shape-and-spatially-varying-reflectance","repo_url":"https://github.com/huizhuo1987/ICCP_DL_PS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"brdf-estimation","task_name":"BRDF estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1512.05278","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}