Image denoising is a fundamental and challenging task in the field of
co...
Recent work on discrete generative priors, in the form of codebooks, has...
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 ...
Due to the difficulty in collecting large-scale and perfectly aligned pa...
In this paper, orthogonal to the existing data and model studies, we ins...
Controllable image denoising aims to generate clean samples with human
p...
With the advent of deep learning methods replacing the ISP in transformi...
The increased resolution of real-world videos presents a dilemma between...
Existing convolutional neural networks widely adopt spatial down-/up-sam...
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 show that pre-trained Generative Adversarial Networks (GANs) such as
...
The lensless pinhole camera is perhaps the earliest and simplest form of...
Low-light image enhancement (LLIE) aims at improving the perception or
i...
Recent development of Under-Display Camera (UDC) systems provides a true...
We propose a novel high dynamic range (HDR) video reconstruction method ...
Indirect Time-of-Flight (iToF) cameras are a promising depth sensing
tec...
We show that pre-trained Generative Adversarial Networks (GANs), e.g.,
S...
This paper reviews the second AIM learned ISP challenge and provides the...
While humans can effortlessly transform complex visual scenes into simpl...
Despite the long history of image and video stitching research, existing...
Scene reconstruction from unorganized RGB images is an important task in...
Depth sensing is crucial for 3D reconstruction and scene understanding.
...
Inverse rendering aims to estimate physical scene attributes (e.g.,
refl...
Time-of-Flight (ToF) cameras require active illumination to obtain depth...
This paper proposes a deep neural architecture, PlaneRCNN, that detects ...
Learning to insert an object instance into an image in a semantically
co...
Learning to insert an object instance into an image in a semantically
co...
Videos contain highly redundant information between frames. Such redunda...
Motion blur is a fundamental problem in computer vision as it impacts im...
Maps are a key component in image-based camera localization and visual S...
The reflections caused by common semi-reflectors, such as glass windows,...
In this paper, we propose spatial propagation networks for learning the
...
We propose a deep learning-based framework for instance-level object
seg...
Estimating surface reflectance (BRDF) is one key component for complete ...
Power consumption is a critical factor for the deployment of embedded
co...