Qi Shan

I graduated from the PhD program of the CSE department of University of Washington, Seattle, supervised by Prof. Brian Curless and Prof. Steve Seitz. I received my MPhil. degree from CSE department of the Chinese University of Hong Kong, and a joint Bachelor degree from Fudan University in China and University College Dublin in Ireland.

My research interests include computer graphics, computer vision, and machine learning.

I am currently leading a research and product development group at Zillow Seattle, working on computer vision/machine learning problems. Send me an email if you are interested in internships or full-time positions.

Email: shanqi-atmark-cs.washington.edu

Publications

LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image,
Chuhang Zou, Alex Colburn, Qi Shan, and Derek Hoiem,
CVPR 2018.
arXiv:1803.08999
Code
RIDI: Robust IMU Double Integration,
Hang Yan, Qi Shan, and Yasutaka Furukawa.
Project Page
Video
arXiv:1712.09004
Panoramic Structure from Motion via Geometric Relationship Detection,
Satoshi Ikehata, Ivaylo Boyadzhiev, Qi Shan, and Yasutaka Furukawa.
arXiv:1612.01256
Video
IM2CAD,
Hamid Izadinia, Qi Shan, and Steven M. Seitz,
CVPR 2017.
arXiv:1608.05137 (August 2016)
Project Page
Accurate Geo-registration by Ground-to-Aerial Image Matching,
Qi Shan, Changchang Wu, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, and Steven M. Seitz,
3DV 2014, oral presentation.
Project Page
Photo Uncrop,
Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, and Steven M. Seitz,

ECCV
2014.

Project Page
A Seattle Times article
Occluding Contours for Multi-View Stereo,
Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, and Steven M. Seitz,

CVPR
2014
.
Project Page

The Visual Turing Test for Scene Reconstruction,
Qi Shan, Riley Adams, Brian Curless, Yasutaka Furukawa, and Steven M. Seitz,

3DV
2013
, oral presentation.
Best Paper Award
.
Project Page
Tone Mapping High Dynamic Range Videos using Wavelets,
Qi Shan, Mark Meyer, Tony DeRose, John Anderson,

Pixar Technical Memo #12-01
, 2012.

Project Page
Refractive Height Fields from Single and Multiple Images,
Qi Shan, Sameer Agarwal, and Brian Curless,

CVPR
2012
.
Project Page
Toward a Visual Pedometer,
Dawei Liu, Qi Shan, and Dan Wu,
SAC 2012
.
Seeing through Obscure Glass,
Qi Shan, Brian Curless, and Tadayoshi Kohno,

ECCV
2010
.
Spatially variant non-blind deconvolution executable
Project Page
Using Optical Defocus to Denoise,
Qi Shan, Jiaya Jia, Sing Bing Kang, and Zenglu Qin,

CVPR
2010
.
Technical report on non-blind deconvolution
Globally Optimized Linear Windowed Tone-Mapping,
Qi Shan, Jiaya Jia, and Michael S. Brown,

TVCG
2010.
Code
Project Page
Fast Image/Video Upsampling,
Qi Shan, Zhaorong Li, Jiaya Jia, and Chi-Keung Tang,

SIGGRAPH
ASIA 2008.
Project Page
High-Quality Motion Deblurring From a Single Image,
Qi Shan, Jiaya Jia, and Aseem Agarwala,

SIGGRAPH
2008.
Project Page
Interactive deblur project page

Interactive deblur YouTube link
Rotational Motion Deblurring of a Rigid Object from a Single Image,
Qi Shan, Wei Xiong, and Jiaya Jia,
ICCV
2007.

 

Released Software

Spatially variant non-blind deconvolution
HDR Tone-mapping   (in Matlab)
Image Upsampling (GPU Enabled)
Video Upsampling
Non-Blind Deconvolution
Single Image Deblur

Contact Info.

Email: shanqi-atmark-cs.washington.edu