Images captured in poorly lit conditions are often corrupted by acquisit...
Large amounts of incremental learning algorithms have been proposed to
a...
Face super-resolution is a technology that transforms a low-resolution f...
Image deblurring continues to achieve impressive performance with the
de...
Guided depth map super-resolution (GDSR), which aims to reconstruct a
hi...
Depth map estimation from images is an important task in robotic systems...
Lossless and near-lossless image compression is of paramount importance ...
Monocular depth estimation is an essential task in the computer vision
c...
The success of deep neural networks greatly relies on the availability o...
One of the main challenges for feature representation in deep learning-b...
Data augmentation (DA) is a widely used technique for enhancing the trai...
Monocular 3D object detection (Mono3D) has achieved tremendous improveme...
Monocular 3D object detection (Mono3D) has achieved unprecedented succes...
Point clouds upsampling is a challenging issue to generate dense and uni...
Monocular depth estimation is a fundamental task in computer vision and ...
This paper aims to address the problem of supervised monocular depth
est...
Robustness of deep neural networks (DNNs) to malicious perturbations is ...
Estimating the risk level of adversarial examples is essential for safel...
We propose an end-to-end image compression and analysis model with
Trans...
Guided filter is a fundamental tool in computer vision and computer grap...
Pre-training has become a standard paradigm in many computer vision task...
To solve the ill-posed problem of hyperspectral image super-resolution
(...
Depth estimation from a single image is an active research topic in comp...
High-resolution (HR) hyperspectral face image plays an important role in...
Learning with noisy labels is an important and challenging task for trai...
Robust loss functions are essential for training deep neural networks wi...
The defocus deblurring raised from the finite aperture size and exposure...
Depth map records distance between the viewpoint and objects in the scen...
We propose a novel joint lossy image and residual compression framework ...
Face super-resolution, also known as face hallucination, which is aimed ...
Person re-identification (ReID) aims at searching the same identity pers...
Image enhancement from degradation of rainy artifacts plays a critical r...
Recently, single gray/RGB image super-resolution reconstruction task has...
Plant diseases serve as one of main threats to food security and crop
pr...
Whole slide imaging (WSI) is an emerging technology for digital patholog...
Hyperspectral image (HSI) denoising is of crucial importance for many
su...
We present FasterSeg, an automatically designed semantic segmentation ne...
More powerful feature representations derived from deep neural networks
...
As a real scenes sensing approach, depth information obtains the widespr...
Blind image deblurring is a challenging problem in computer vision, whic...
Mesh denoising is a critical technology in geometry processing, which ai...
Label information plays an important role in supervised hyperspectral im...
Image denoising and high-level vision tasks are usually handled independ...
A renowned information-theoretic formula by Shannon expresses the mutual...
Blind image deblurring, i.e., deblurring without knowledge of the blur
k...
Blind image deblurring, i.e., deblurring without knowledge of the blur
k...
High resolution datasets of population density which accurately map
spar...
In the last several years, remote sensing technology has opened up the
p...
Conventionally, image denoising and high-level vision tasks are handled
...
Learning from weakly-supervised data is one of the main challenges in ma...