- Dr. Michael S. Brown , National University of Singapore.
Title: Color and Commodity Cameras: The Good, The Bad, and The Ugly.
Michael S. Brown obtained his BS and PhD in Computer Science from the University of Kentucky in 1995 and 2001 respectively. He was a visiting PhD student at the University of North Carolina at Chapel Hill from 1998-2000. Dr. Brown has held positions at the Hong Kong University of Science and Technology (2001-2004), California State University - Monterey Bay (2004-2005), and Nanyang Technological University (2005-2007). He joined the School of Computing at the National University of Singapore in 2007 where he is currently an associate professor and vice dean (corporate relations). Dr. Brown's research interests include computer vision, image processing and computer graphics. He has served as an area chair for CVPR, ICCV, ECCV, and ACCV and is currently an associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and the International Journal of Computer Vision (IJCV). Dr. Brown received the HKUST Faculty Teaching Award (2002), the NUS Young Investigator Award (2008), the NUS Faculty Teaching Award (for AY08/09, AY09/10, AY10/11), and the NUS Annual Teaching Excellence Award (ATEA) for AY09/10.
- Dr. Peter Gehler , University of Tübingen.
Peter Gehler is a research group leader and senior researcher at the Bernstein Center of Computational Neuroscience (BCCN) of the University of Tübingen and the Max Planck Institute for Intelligent Systems. Before, he was postdoctoral researcher at ETH Zurich, temporary Professor at TU Darmstadt, and Junior Research Group Leader at the Max Planck Institute for Informatik, Saarbrücken. He did his PhD studies in the Empirical Inference group at the Max Planck Institute for Biological Cybernetics, Tübingen. Peter serves as area chair at ICCV and ECCV and Associate Editor of TPAMI. In 2015 he was the program chair of GCPR. His main research focus lies on inference methods that are able to relate visual scenes with physical properties of the real world.
Talks for contributed papers are intended to be 20 minutes long (including questions).
|8:45-9:30||Keynote: Michael Brown (National Univ. of Singapore), Color and Commodity Cameras: The Good, the Bad, and the Ugly.|
|09:30-09:45||Oral Session:Xiandou Zhang (Hangzhou Dianzi University), Brian Funt (Simon Fraser University), Hamidreza Mirzaei (Simon Fraser University), Metamer Mismatching and its Consequences for Predicting How Colours are Affected by the Illuminant.||09:50-10:10||Oral Session:Sheetal Gupta (IIT Madras), Rajagopalan Ambasamudram (IIT Madras), Gunasekaran Seetharaman (Information Directorate AFRL), HDR Recovery under Rolling Shutter Distortions.|
|10:30-11:10||Keynote: Peter Gehler (University of Tübingen). Intrinsic Videos and the Bilateral Filter.|
|11:10-11:35||Oral Session:Roshanak Zakizadeh (University of East Anglia), Michael Brown (National University of Singapore), Graham Finlayson (University of East Anglia), A Hybrid Strategy For Illuminant Estimation Targeting Hard Images.|
|11:40-11:45||Oral Session:Youngjin Yoon (KAIST), Hae-Gon Jeon (KAIST), Donggeun Yoo (KAIST), Joon-Young Lee (KAIST), In So Kweon (KAIST), Learning a Deep Convolutional Network for Light-Field Image Super-Resolution.|
|11:50-12:05||Oral Session:Yusuke Monno (Tokyo Institute of Technology), Masayuki Tanaka (Tokyo Institute of Technology), Masatoshi Okutomi (Tokyo Institute of Technology), N-to-sRGB Mapping for Single-Sensor Multispectral Imaging.|
Description of the workshop
When light interacts with surfaces and participating media, it is altered in terms of its spectrum, polarization state, and spatial and angular distributions. Modeling and analyzing these processes has a long history in vision, and it has deepened our understanding of biological vision systems and enabled the development of a variety of computational tools for analyzing and organizing visual data.
Over the last decade, with the acceleration of digital photography and the advances in appearance scanners, image sensors, and displays, we have seen explosive growth in the amount of visual data that is available, and equally explosive growth in the opportunities for image understanding by machines.
This workshop will leverage this growth and exploit these opportunities by providing new insights for the understanding of color and photometry in computer vision. As color and photometry are shared among various research fields, this workshop places them at the junctions of different areas, including color science, applied optics, computational photography, computer vision, computer graphics, and machine learning. It seeks to enable knowledge discovery using area-specific expertise and cross-understanding.
We encourage researchers to formulate innovative color theories, color representations, and color processing techniques, and to evaluate their effectiveness. We also encourage new theories and processes for organizing images and inferring scene information from images through analysis of photometry and/or color that is motivated by perception, physics, and phenomenology. We are soliciting original contributions that address a wide range of theoretical and practical issues including, but not limited to:
- Theory: Color spaces; reflection models; scattering models; light transport; multi-spectral, hyper-spectral, and polarization models; appearance analysis; color appearance models.
- Sensors: Imaging systems; active illumination systems; spectrum and polarization sensing; light probes; shape and material scanners; radiometric and colorimetric calibration.
- Image/Video Processing: Filtering, enhancement, feature detection, and segmentation informed by color and/or photometry; white balance; relighting; image decomposition via intrinsic images, specularity removal, and shadow removal; color texture; colorization.
- Material, Object, Scene, and Video Recognition: Photometric invariants; color invariants; material recognition; lighting estimation; shape estimation; color saliency; color constancy; color descriptors and matching.
- Vision Science: Material perception; shape perception; lighting perception; lightness and color perception.
- Applications: Industrial inspection; human computer interaction; navigation; medical diagnosis; biology and biomedicine.
- Submission Deadline: September 9 (5pm Pacific Time).
- Notification of Acceptance: October 4th
- Camera-ready Deadline: October 14th.
- Workshop: December 11 (AM only).
- Theo Gevers (University of Amsterdam, The Netherlands)
- Jose Alvarez (NICTA, Australia)
- Joost van de Weijer (Computer Vision Center, Spain)
- Arjan Gijsenij (Akzo Nobel, The Netherlands)
- The submission site is https://cmt2.research.microsoft.com/CPCV2015/
- The maximum paper length is 8 pages using the ICCV main conference format.
- Submissions will be rejected without review if they exceed the maximum length or violate the double-blind policy.
- Simone Bianco, Universita degli Studi di Milano-Bicocca, Italy
- Mark Drew, Simon Fraser University, Canada
- Takahiko Horiuchi, Chiba University, Japan
- David Jacobs, University of Maryland at College Park, USA
- Sanjeev Koppal, Harvard University, USA
- Reiner Lenz, Linkoping University, Sweden
- Marcel Lucassen, University of Amsterdam, The Netherlands
- Michael S. Brown, NUS Singapore
- Christian Riess, Friedrich-Alexander-Universitat Erlangen-Nurnberg
- Yoshitsugu Manabe, Chiba University, Japan
- Roberto Manduchi, UC Santa Cruz, USA
- Jiri Matas, Czech Technical University, Czech Republic
- Damien Muselet, Universite Jean Monnet, France
- Ko Nishino, Drexel University, USA
- Alessandro Rizzi, University of Milano, Italy
- Imari Sato, National Institute of Informatics, Japan
- Yoichi Sato, University of Tokyo, Japan
- Shoji Tominaga, Chiba University, Japan
- Roshanak Zakizadeh, University of East Anglia, Norwich
- Alain Tremeau, Universite Jean Monnet, France
- Robby Tan, Yale NUS college, Singapore
- Raimondo Schettini, Universita degli Studi di Milano-Bicocca, Italy
- Antonio Robles-Kelly, NICTA, Australia
- Chen Hwann-Tzong, National Tsing Hua University, Taiwan
- Javier Vazquez, Universitat Pompeu Fabra, Spain
- Kuk-Jin Yoon, Gwangju Institute of Science and Technology, Korea