Images or videos captured by the Under-Display Camera (UDC) suffer from
...
In recent years, Transformer networks are beginning to replace pure
conv...
By hiding the front-facing camera below the display panel, Under-Display...
Understanding human interaction with objects is an important research to...
Deep learning based methods have achieved significant success in the tas...
Current deep learning methods for low-light image enhancement (LLIE)
typ...
Facial expression is related to facial muscle contractions and different...
Image restoration in adverse weather conditions is a difficult task in
c...
Rain-by-snow weather removal is a specialized task in weather-degraded i...
As the quality of optical sensors improves, there is a need for processi...
Image restoration under hazy weather condition, which is called single i...
Face Restoration (FR) aims to restore High-Quality (HQ) faces from
Low-Q...
Vision transformers have shown great success on numerous computer vision...
Blind Face Restoration (BFR) aims to construct a high-quality (HQ) face ...
Recent deep face hallucination methods show stunning performance in
supe...
Hazy images reduce the visibility of the image content, and haze will le...
Single-image super-resolution (SR) and multi-frame SR are two ways to su...
Rain is a common natural phenomenon. Taking images in the rain however o...
Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruc...
Video deraining is an important task in computer vision as the unwanted ...
Images captured in snowy days suffer from noticeable degradation of scen...
Rain streaks and rain drops are two natural phenomena, which degrade ima...
Video deblurring models exploit consecutive frames to remove blurs from
...
Although deep learning-based methods have dominated stereo matching
lead...
Learning matching costs has been shown to be critical to the success of ...
Sign language translation (SLT) aims to interpret sign video sequences i...
Informative features play a crucial role in the single image super-resol...
Existing deep learning methods for image deblurring typically train mode...
Effective and Efficient spatio-temporal modeling is essential for action...
Camera shake or target movement often leads to undesired blur effects in...