Neural radiance fields (NeRF) have shown great success in novel view
syn...
This paper proposes a new framework for low-light image enhancement by
s...
Neural radiance fields (NeRF) show great success in novel view synthesis...
Various recent methods attempt to implement rotation-invariant 3D deep
l...
Previous studies show the necessity of global and local adjustment for i...
To facilitate video denoising research, we construct a compelling datase...
Video frame interpolation (VFI), which aims to synthesize intermediate f...
For video frame interpolation (VFI), existing deep-learning-based approa...
Pre-training has marked numerous state of the arts in high-level compute...
Long-range temporal alignment is critical yet challenging for video
rest...
As a basic component of SE(3)-equivariant deep feature learning, steerab...
Reference-based image super-resolution (RefSR) has shown promising succe...
Single image super-resolution (SISR) deals with a fundamental problem of...
We consider the single image super-resolution (SISR) problem, where a
hi...
Video instance segmentation (VIS) aims to segment and associate all inst...
Skeleton-based action recognition has attracted research attentions in r...
In this work, we propose an interactive system to design diverse high-qu...
Video super-resolution (VSR) aims to utilize multiple low-resolution fra...
Recent advances in the joint processing of images have certainly shown i...
Estimating 3D human pose from a single image is a challenging task. This...
Estimating 3D human pose from a single image is a challenging task. This...
The ability to identify the static background in videos captured by a mo...
In this paper, a novel deep-learning based framework is proposed to infe...
Although significant advances have been made in the area of human poses
...
2D object proposals, quickly detected regions in an image that likely co...
In this paper, we categorize fine-grained images without using any objec...