Tao Yue


Associate Professor

Nanjing University

School of Electronic Science and Technology

Computational Perception Lab

E-Mail: yuetao@nju.edu.cn

Tao Yue received his B.S. degree from Northwestern Polytechnic University in 2009 and the Ph.D. degree from Tsinghua University (supervised by Prof. Qionghai Dai) in 2015, respectively. After then, he joined Nanjing University as an associate professor at School of Electronic Science and Technology. He stayed in University of Washington (Seattle) from 2013 to 2014 as a visit student, under the supervising of Prof. Ming-Ting Sun, Dr. Zhengyou Zhang and Dr. Jue Wang.

Currectly, he's working with Xuemei Hu on the areas of Image Processing, Computer Vision and Computational Photography.

Research Projects

Efficient Method for High Quality Removal of Non-uniform Blur in Wavelet Domain

IEEE Trans. Circuits Syst. Video Technol. 2016, Project Page, Paper

We propose an efficient non-uniform deconvolution method in wavelet domain for dealing with the camera motion caused spatially-varying blurry images.

Blind Optical Aberration Correction by Exploring Geometric and Visual Priors

CVPR 2015, Project Page, Paper

We propose a computational approach for blind aberration removal from a single image by exploring various geometric and visual priors.

Image Quality Enhancement Using Original Lens via Optical Computing

Opt. Express 2014, Project Page, Paper

We try to enhance the images degraded by the optical aberrations (e.g. spherical aberration, coma, chromatic aberration and so on) by using optical computating.

Hybrid Image Deblurring by Fusing Edge and Power Spectrum Information

ECCV 2014, Project Page, Paper

We try to fusing the two main kinds of kernel estimation algorithms for blind deblurring together to achieve better robustness and performance.

Deblur a Blurred RGB Image with a Sharp NIR Image Through Local Linear Mapping

ICME 2014, Project Page, Paper

We try to recover the sharp RGB images from the blurred RGB images and corresponding sharp NIR images by using the local linear mappings.

High-Dimensional Camera Shake Removal with Given Depth Map

IEEE Trans. Image Process. 2014, Project Page, Paper

We try to estimate the high-dimensional camera motion from a single blurred image with the given depth map, and then remove the nonuniform blurry effect.

Non-uniform Image Deblurring Using an Optical Computing System

Computer & Graphics 2013, Paper; CVPRW on CCD 2013 (Best Paper), Paper

We accelerate the image restoration algorithm for camera shake caused nonuniform blur by using a projector-camera system on a high-dimensional motion platform.


Publications

2019
2018
2017
2016
2015
2014
2013