Shading‐Based Surface Recovery Using Subdivision‐Based Representation

Simple item page
dc.contributor.authorDeng, Tengen_US
dc.contributor.authorZheng, Jianminen_US
dc.contributor.authorCai, Jianfeien_US
dc.contributor.authorCham, Tat‐Jenen_US
dc.contributor.editorChen, Min and Benes, Bedrichen_US
dc.date.accessioned2019-03-17T09:56:59Z
dc.date.available2019-03-17T09:56:59Z
dc.date.issued2019
dc.description.abstractThis paper presents subdivision‐based representations for both lighting and geometry in shape‐from‐shading. A very recent shading‐based method introduced a per‐vertex overall illumination model for surface reconstruction, which has advantage of conveniently handling complicated lighting condition and avoiding explicit estimation of visibility and varied albedo. However, due to its discrete nature, the per‐vertex overall illumination requires a large amount of memory and lacks intrinsic coherence. To overcome these problems, in this paper we propose to use classic subdivision to define the basic smooth lighting function and surface, and introduce additional independent variables into the subdivision to adaptively model sharp changes of illumination and geometry. Compared to previous works, the new model not only preserves the merits of the per‐vertex illumination model, but also greatly reduces the number of variables required in surface recovery and intrinsically regularizes the illumination vectors and the surface. These features make the new model very suitable for multi‐view stereo surface reconstruction under general, unknown illumination condition. Particularly, a variational surface reconstruction method built upon the subdivision representations for lighting and geometry is developed. The experiments on both synthetic and real‐world data sets have demonstrated that the proposed method can achieve memory efficiency and improve surface detail recovery.This paper presents subdivision‐based representations for both lighting and geometry in shape‐from‐shading. A very recent shading‐based method introduced a per‐vertex overall illumination model for surface reconstruction, which has advantage of conveniently handling complicated lighting condition and avoiding explicit estimation of visibility and varied albedo. However, due to its discrete nature, the per‐vertex overall illumination requires a large amount of memory and lacks intrinsic coherence. To overcome these problems, in this paper we propose to use classic subdivision to define the basic smooth lighting function and surface, and introduce additional independent variables into the subdivision to adaptively model sharp changes of illumination and geometry. Compared to previous works, the new model not only preserves the merits of the per‐vertex illumination model, but also greatly reduces the number of variables required in surface recovery and intrinsically regularizes the illumination vectors and the surface. These features make the new model very suitable for multi‐view stereo surface reconstruction under general, unknown illumination condition. Particularly, a variational surface reconstruction method built upon the subdivision representations for lighting and geometry is developed. The experiments on both synthetic and real‐world data sets have demonstrated that the proposed method can achieve memory efficiency and improve surface detail recovery.en_US
dc.description.number1
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume38
dc.identifier.doi10.1111/cgf.13539
dc.identifier.issn1467-8659
dc.identifier.pages417-428
dc.identifier.urihttps://doi.org/10.1111/cgf.13539
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13539
dc.publisher© 2019 The Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectimage‐based modelling
dc.subjectI.4.8 [Image Processing and Computer Vision]: Scene Analysis—Shading
dc.subjectShape
dc.titleShading‐Based Surface Recovery Using Subdivision‐Based Representationen_US
Files
Collections
38-Issue 1