Exploiting pre-trained diffusion models for restoration has recently bec...
Flow-based propagation and spatiotemporal Transformer are two mainstream...
Local motion blur commonly occurs in real-world photography due to the m...
Artificial lights commonly leave strong lens flare artifacts on the imag...
Developing and integrating advanced image sensors with novel algorithms ...
We present a novel approach to leverage prior knowledge encapsulated in
...
Developing and integrating advanced image sensors with novel algorithms ...
Developing and integrating advanced image sensors with novel algorithms ...
We propose a novel unsupervised backlit image enhancement method, abbrev...
Reflective flare is a phenomenon that occurs when light reflects inside
...
Ultra-High-Definition (UHD) photo has gradually become the standard
conf...
Deblurring can not only provide visually more pleasant pictures and make...
To improve the performance of blind face restoration, recent works mainl...
Artificial lights commonly leave strong lens flare artifacts on images
c...
Developing and integrating advanced image sensors with novel algorithms ...
Developing and integrating advanced image sensors with novel algorithms ...
Developing and integrating advanced image sensors with novel algorithms ...
Developing and integrating advanced image sensors with novel algorithms ...
Developing and integrating advanced image sensors with novel algorithms ...
We present Curve Distillation, CuDi, for efficient and controllable expo...
Blind face restoration is a highly ill-posed problem that often requires...
The exploitation of long-term information has been a long-standing probl...
Night photography typically suffers from both low light and blurring iss...
The diversity and complexity of degradations in real-world video
super-r...
A recurrent structure is a popular framework choice for the task of vide...
This paper reviews the first NTIRE challenge on quality enhancement of
c...
This paper presents a new method, called FlexiCurve, for photo enhanceme...
Recent reference-based face restoration methods have received considerab...
Non-local self-similarity in natural images has been well studied as an
...
Crowd counting is an important yet challenging task due to the large sca...
Deep hashing methods have been proved to be effective and efficient for
...
Inferring the 3D shape of an object from an RGB image has shown impressi...
Video deblurring is a challenging task due to the spatially variant blur...
Nowadays stereo cameras are more commonly adopted in emerging devices su...
Recovering the 3D representation of an object from single-view or multi-...