国立大学法人東北大学電気通信研究所公式ウェブサイト|Research Institute of Electrical Communication Tohoku University

“Robust Photometric Stereo” 講演会

日時:2013年3月28日(木)14:30~
場所:東北大学電気通信研究所 1号館S棟3階 S305セミナー室
題目:“Robust Photometric Stereo”
講師:松下 康之 先生(Lead Researcher in Visual Computing Group,Microsoft Research Asia)


“Robust Photometric Stereo”  講演会のご案内

Microsoft Research Asia (MSRA)の主任研究員で,東北大学電気通信研究所の客員准教授も務めていただいている松下 康之先生の講演会を開催いたします.松下先生は,MSRAで主にコンピュータビジョンの研究に従事しておられます.事前申し込みは不要ですので,ご興味を持っていただけましたら,ご自由にお集まりください.

  • 日時  :2013年3月28日(木)14:30~
  • 場所  :東北大学電気通信研究所 1号館S棟3階 S305セミナー室
  • 題目  :“Robust photometric stereo”
  • 講師  :松下 康之 先生
    Lead Researcher in Visual Computing Group, Microsoft Research Asia
Abstract:

Photometric stereo estimates surface normals of a scene from a set of observations recorded under varying lightings. After the original work presented by Woodham in 1980, which assumes a Lambertian reflectance and directional lighting, a number of theoretical and experimental studies have been conducted for relaxing the restricting assumptions. Ultimately, a “robust” photometric stereo method should be able to accurately recover surface normals of a scene made of arbitrary optic properties. It is, however, still a challenging task to build such a photometric stereo system that works in arbitrary conditions because of the complexity of the real-world image formation process.

In this talk, we first give an introduction to photometric 3D modeling methods. We then briefly discuss two types of approaches to robust photometric stereo from our recent works; robust regression and model relaxation approaches. In the robust regression approach, we introduce methods where we cast the photometric stereo problem as a robust regression problem. We also talk about the direction of generalizing reflectance models so that more diverse and realistic reflectances can be handled (and thus, results in accurate estimates). Finally, we discuss the future directions of shape measurement and robust photometric stereo methods.

Speaker bio:

Yasuyuki Matsushita received his B.S., M.S. and Ph.D. degrees in EECS from the University of Tokyo in 1998, 2000, and 2003, respectively. He joined Microsoft Research Asia in April 2003. He is a Lead Researcher in Visual Computing Group. His areas of research are computer vision (photometric techniques, such as radiometric calibration, photometric stereo, shape-from-shading), computer graphics (image relighting, video analysis and synthesis). He is on the editorial board member of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV, The Visual Computer Journal, and Encyclopedia of Computer Vision, and Associate Editor-in-Chief for IPSJ Journal of Computer Vision and Applications (CVA). He served/is serving as a Program Co-Chair of PSIVT 2010, 3DIMPVT 2011, and ACCV 2012. He is appointed as a Guest Associate Professor at Osaka University (April 2010-), Visiting Associate Professor at National Institute of Informatics (April 2011-) and Tohoku University (April 2012 – ), Japan. He is a senior member of IEEE.

matsushita

問い合わせ先

電気通信研究所 システム・ソフトウェア研究部門 情報コンテンツ研究室

(教授)北村 喜文