Self-supervised monocular scene flow estimation, aiming to understand bo...
Removing raindrops in images has been addressed as a significant task fo...
Polarization information of light in a scene is valuable for various ima...
Depth reconstruction and hyperspectral reflectance reconstruction are tw...
In existing self-supervised depth and ego-motion estimation methods,
ego...
Single image deraining is typically addressed as residual learning to pr...
Gastroendoscopy has been a clinical standard for diagnosing and treating...
The combined use of multiple modalities enables accurate pedestrian dete...
Deep convolutional networks have become the mainstream in computer visio...
In this paper we introduce a new camera localization strategy designed f...
Reconstructing an object's high-quality 3D shape with inherent spectral
...
In this paper, we present a robust and efficient Structure from Motion
p...
A lighting-based multispectral imaging system using an RGB camera and a
...
In this paper, we propose a deep snapshot high dynamic range (HDR) imagi...
Future frame prediction in videos is a challenging problem because video...
Consecutive LiDAR scans compose dynamic 3D sequences, which contain more...
A division-of-focal-plane or microgrid image polarimeter enables us to
a...
A polarization camera has great potential for 3D reconstruction since th...
Pipe inspection is a critical task for many industries and infrastructur...
Classification for degraded images having various levels of degradation ...
Gastric endoscopy is a standard clinical process that enables medical
pr...
In this paper, we propose an automatic labeled sequential data generatio...
In this paper, we propose a novel projector-camera system for practical ...
Visual localization in large and complex indoor scenes, dominated by wea...
Gastric endoscopy is a common clinical practice that enables medical doc...
Deep learning techniques are rapidly advanced recently, and becoming a
n...
Following improvements in deep neural networks, state-of-the-art network...
Image restoration from a single image degradation type, such as blurring...
A low-light image enhancement is a highly demanded image processing
tech...
Blind image restoration processors based on convolutional neural network...
Structure from Motion (SfM) using imagery that involves extreme appearan...
We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photog...
Visual localization enables autonomous vehicles to navigate in their
sur...