资源论文Surface Normal Deconvolution: Photometric Stereo for Optically Thick Translucent Ob jects

Surface Normal Deconvolution: Photometric Stereo for Optically Thick Translucent Ob jects

2020-04-06 | |  59 |   45 |   0

Abstract

This paper presents a photometric stereo method that works for optically thick translucent ob jects exhibiting subsurface scattering. Our method is built upon the previous studies showing that subsur- face scattering is approximated as convolution with a blurring kernel. We extend this observation and show that the original surface normal convolved with the scattering kernel corresponds to the blurred surface normal that can be obtained by a conventional photometric stereo tech- nique. Based on this observation, we cast the photometric stereo problem for optically thick translucent ob jects as a deconvolution problem, and develop a method to recover accurate surface normals. Experimental re- sults of both synthetic and real-world scenes show the effectiveness of the proposed method.

上一篇:Stacked Deformable Part Model with Shape Regression for Ob ject Part Localization

下一篇:Read My Lips: Continuous Signer Independent Weakly Supervised Viseme Recognition

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...