Chika Inoshita

Data set release.
Project page of photometric stereo for translucent objects

4/2014-                 Special research students, (Nara Institute of Science and Technology)

4/2012-   Ph.D candidate of Information Science, Graduate School of Information Science and Technology, Osaka University.
3/2012     M.S. Information Science, Graduate School of Information Science and Technology, Osaka University.
3/2010     B.S. Computer Science, School of Engineering Science, Osaka University.
3/2008     A.S. Information Engineering, Takuma National College of Technology.

4/2013-                 Research Fellow (The Japan Society for the Promotion of Science)
6/2012-3/2013     Visiting Researcher (Microsoft Research Asia)
6/2012-3/2013     Research Assistant (ISIR, Osaka University)
4/2012-3/2013     Specially Appointed Researcher (ISIR, Osaka University)
10/2011-2/2012   Tutor (Graduate School of Information Science and Technology, Osaka University)
10/2011-2/2012   TA: Programming B (School of Engineering Science, Osaka University)
4/2010-10/2010   TA: Programming C (School of Engineering Science, Osaka University)

• TOEIC　Score： 785
• Software Design and Development Engineer
• Fundamental Information Technology Engineer
• Systems Administrator

Computer Vision

• Photometric analysis: Scattering Analysis, Shape measurement
• Computational Photography
• Image processing: Deblurring

Photometric stereo for translucent objects

Abstract This paper presents a photometric stereo method that works for optically thick translucent objects exhibiting subsurface scattering. Our method is built upon the previous studies showing that subsurface 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 technique. Based on this observation, we cast the photometric stereo problem for optically thick translucent objects as a deconvolution problem, and develop a method to recover accurate surface normals. Experimental results of both synthetic and real-world scenes show the effectiveness of the proposed method. Publication ECCV2014 [Project page][Pre-print(PDF)][Poster(PDF)][Video]

Full-dimensional Sampling and Analysis of BSSRDF

Abstract Full-dimensional (8-D) BSSRDF completely expresses various light interactions on object surface such as reflection and subsurface scattering. However, it is difficult to sample full-dimensional BSSRDF because it requires many illuminations and observations from various directions. There are many research which approximated BSSRDF as a low-dimensional function by only considering the medium as homogeneous or assuming isotropic scattering. Therefore, in this research, we show a novel sampling and analyzing method for full-dimensional BSSRDF of real scenes. We sample the BSSRDF using a polyhedral mirror system to place a lot of virtual cameras and projectors. In addition, we propose a method of decomposition of BSSRDF into isotropic and anisotropic components for scattering analysis. We show the empirical characteristics of subsurface scattering inside a real medium by analyzing sampled full-dimensional BSSRDF. Publication IPSJ Transactions on CVA, 2013 [J-STAGE]

Shape from Single Scattering for Translucent Objects

Abstract Translucent objects strongly scatter incident light. Scattering makes the problem of estimating shape of translucent objects difficult, because reflective or transmitted light cannot be reliably extracted from the scattering. In this paper, we propose a new shape estimation method by directly utilizing scattering measurements. Although volumetric scattering is a complex phenomenon, single scattering can be relatively easily modeled because it is a simple one-bounce collision of light to a particle in a medium. Based on this observation, our method determines the shape of objects from the observed intensities of the single scattering and its attenuation. We develop a solution method that simultaneously determines scattering parameters and the shape based on energy minimization. We demonstrate the effectiveness of the proposed approach by extensive experiments using synthetic and real data. Publication ECCV2012 [Pre-print(PDF)][Poster(PDF)][Video(wmv)]

Ringing Detector for Deblurring based on Frequency Analysis of PSF

Abstract Many deblurring techniques have been proposed to restore blurred images resulting from camera motion. A major problem in the restoration process is that the deblurred images often include wave-like artifacts called ringing. In this paper, we propose a ringing detector that distinguishes the ringing artifacts from natural textures included in images. In designing the ringing detector, we focus on the fact that ringing artifacts are caused by the null frequency of the point-spread function. Ringing are detected by evaluating whether the deblurred image contains sine waves corresponding to the null frequencies across the entire image with uniform phase. By combining the ringing detector with a deblurring process, we can reduce ringing artifacts in the restored images. We demonstrate the effectiveness of the proposed ringing detector in experiments with synthetic and real images. Publication IPSJ Transactions on CVA, 2011 [PDF]

1. C. Inoshita, S. Tagawa, M. Md. Abdul, Y. Mukaigawa, Y. Yagi, ``Full-dimensional Sampling and Analysis of BSSRDF'', IPSJ Transactions on Computer Vision and Applications, Vol. 5, pp.119-123, 2013．[J-STAGE]
2. C. Inoshita, Y. Mukaigawa, Y. Yagi, ``Ringing Detector for Deblurring based on Frequency Analysis of PSF'', IPSJ Transactions on Computer Vision and Applications, Vol. 3, pp.236-247, 2011. [PDF]

1. C. Inoshita, Y. Mukaigawa, Y. Matsushita, Y. Yagi, ``Surface Normal Deconvolution: Photometric Stereo for Optically Thick Translucent Objects'', The 13th European Conference on Computer Vision (ECCV2014), Sep. 2014. (Acceptance rate: 363/1444=25.1%) [Project page][Pre-print(PDF)][Poster(PDF)][Video]
2. C. Inoshita, Y. Mukaigawa, Y. Matsushita, Y. Yagi, ``Shape from Single Scattering for Translucent Objects'', The 12th European Conference on Computer Vision (ECCV2012), Oct. 2012. (Acceptance rate: 408/1437=28.4%) [Pre-print(PDF)][Poster(PDF)][Video(wmv)]

1. C. Inoshita, Y. Mukaigawa, Y. Matsushita, Y. Yagi, ``Photometric Stereo for Transclucent Objects using Surface Normal Deconvolution'', The 18th SANKEN International Symposium, Dec. 2014.
2. C. Inoshita, Y. Mukaigawa, Y. Matsushita, Y. Yagi, ``Photometric Stereo for Translucent Objects by Surface Normal Deconvolution'', The 9th International Workshop on Robust Computer Vision, (IWRCV2014), Dec. 2014.
3. C. Inoshita, S.Tagawa, Md. A. Mannan, Y. Mukaigawa, Y. Yagi, ``Measurement and analysis of full-dimensional BSSRDF'', The 8th International Workshop on Robust Computer Vision, (IWRCV2014), Jan. 2014.
4. C. Inoshita, Y. Mukaigawa, Y. Matsushita, Y. Yagi, ``Shape Estimation Based on Attenuation of Single Scattering for Translucent Objects'', The 7th International Workshop on Robust Computer Vision, Jan., 2013.
5. C. Inoshita, Y. Mukaigawa, Y. Yagi, ``Shape Estimation Based on Attenuation of Single Scattering'', A Joint Workshop between Osaka-Univ. and Peking-Univ. Groups, Jul. 2011.

1. Microsoft Research Fellowship Nomination Award Oct., 2012.

• Yagi Laboratory, ISIR, Osaka University
• Optical Media Interface Lab, NAIST
• Graduate school of Information Science and Technology, Osaka University

• KansaiCVPRML study group