Person re-identification (re-ID) requires densely distributed cameras. I...
In recent years, single-frame image super-resolution (SR) has become mor...
Despite the success in large-scale text-to-image generation and
text-con...
Polarization is a fundamental property of light that encodes abundant
in...
Seeing-in-the-dark is one of the most important and challenging computer...
Adversarial attacks on thermal infrared imaging expose the risk of relat...
This paper studies the challenging problem of recovering motion from blu...
Video deblurring is a highly under-constrained problem due to the spatia...
We study the challenging problem of recovering detailed motion from a si...
Polarized color photography provides both visual textures and object
sur...
This paper proposes the first real-world rolling shutter (RS) correction...
Most computer vision systems assume distortion-free images as inputs. Th...
Rolling shutter (RS) distortion can be interpreted as the result of pick...
Although considerable progress has been made in semantic scene understan...
Enhancing the visibility in extreme low-light environments is a challeng...
Real-time video deblurring still remains a challenging task due to the
c...
Recovering the 3D geometry of a purely texture-less object with generall...
This paper proposes a simple method which solves an open problem of
mult...
Joint rolling shutter correction and deblurring (RSCD) techniques are
cr...
To reconstruct spectral signals from multi-channel observations, in
part...
The current industry practice for 24-hour outdoor imaging is to use a si...
Thanks to the latest progress in image sensor manufacturing technology, ...
Stereo relative pose problem lies at the core of stereo visual odometry
...
We propose a fully automatic system to reconstruct and visualize 3D bloo...
A series of methods have been proposed to reconstruct an image from
comp...