Existing face restoration models have relied on general assessment metri...
Present-day deep learning-based motion deblurring methods utilize the pa...
Commercially available light field cameras have difficulty in capturing ...
Facial image super-resolution (SR) is an important preprocessing for fac...
In recent decades, 3D morphable model (3DMM) has been commonly used in
i...
360 images represent scenes captured in all possible viewing directions....
Restoring a sharp light field image from its blurry input has become
ess...
Synthesizing a densely sampled light field from a single image is highly...
Removing camera motion blur from a single light field is a challenging t...