Shumian Xin

I am a fifth-year PhD student in the Robotics Institute at Carnegie Mellon University, working with Prof. Ioannis Gkioulekas and Prof. Srinivasa Narasimhan on computational imaging research. I received my Master degree in Electrical and Computer Engineering from CMU in 2016, and my Bachelor degree in Electrical Engineering from Xi'an Jiaotong University in 2015.

My research interests are in the area of computer vision and computational imaging. I have been working on projects on non-line-of-sight imaging, dual-pixel defocus estimation and deblurring, as well as specular object reconstruction.

I interned at Google Research in summer 2020 (hosted by Rahul Garg and Neal Wadhwa).

Email  /  CV  /  Google Scholar

profile photo
A Theory of Fermat Paths for Non-Line-of-Sight Shape Reconstruction
Shumian Xin, Sotiris Nousias, Kiriakos N. Kutulakos,
Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan, Ioannis Gkioulekas
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
(Oral Presentation, Best Paper Award)
project page / paper / code
Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image
Shumian Xin, Neal Wadhwa, Tianfan Xue, Jonathan Barron,
Pratul Srinivasan, Jiawen Chen, Ioannis Gkioulekas, Rahul Garg
IEEE International Conference on Computer Vision (ICCV), 2021
(Oral Presentation)
project page / paper / code
Service and Teaching
Reviewer, IEEE Transactions on computational imaging (TCI), Optical Express, ICCV 2021
Teaching Assistant, CMU, 16-720 Computer Vision, Fall 2019 & Spring 2020

Template from Jon Barron. Last updated in October 2021.