Monocular depth estimation has drawn widespread attention from the visio...
Traffic accident detection and anticipation is an obstinate road safety
...
Dark videos often lose essential information, which causes the knowledge...
Online unsupervised video object segmentation (UVOS) uses the previous f...
Image keypoints and descriptors play a crucial role in many visual
measu...
This work aims to estimate a high-quality depth map from a single RGB im...
Model-based single image dehazing algorithms restore haze-free images wi...
Unsupervised monocular trained depth estimation models make use of adjac...
Unsupervised video object segmentation (UVOS) aims at automatically
sepa...
While action recognition (AR) has gained large improvements with the
int...
Existing shape from focus (SFF) techniques cannot preserve depth edges a...
Deep stereo matching has made significant progress in recent years. Howe...
The generative adversarial network (GAN) is successfully applied to stud...
Existing methods detect the keypoints in a non-differentiable way, there...
Model-based single image dehazing algorithms restore images with sharp e...
Semi-supervised video object segmentation (VOS) aims to segment a few mo...
Keypoints matching is a pivotal component for many image-relevant
applic...
It is challenging to stitch multiple images with different exposures due...
Spatially varying exposure (SVE) is a promising choice for high-dynamic-...
There are shadow and highlight regions in a low dynamic range (LDR) imag...
Due to possibly changing pose of a movable object and nonholonomic const...
Model driven single image dehazing was widely studied on top of differen...
Light detection and ranging (LiDAR) on a moving agent could suffer from
...
Localizing pre-visited places during long-term simultaneous localization...
Inertial Measurement Units (IMUs) are interceptive modalities that provi...
A small ISO and a small exposure time are usually used to capture an ima...
Localization can be achieved by different sensors and techniques such as...
Employing an inertial measurement unit (IMU) as an additional sensor can...
Deep learning based methods have penetrated many image processing proble...
It is challenging to design a high speed tracking approach using l1-norm...
In this article, we show that solving the system of linear equations by
...
Retinal fundus photographs have been used in the diagnosis of many ocula...