The booming interest in adversarial attacks stems from a misalignment between human
vision and a deep neural network (DNN),\ie~ a human imperceptible perturbation fools the …

Video deblurring is a highly under-constrained problem due to the spatially and temporally
varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the …

In recent years, the removal of motion blur in photographs has seen impressive progress in
the hands of deep learning-based methods, trained to map directly from blurry to sharp …

Optical flow is a classical task that is important to the vision community. Classical optical flow
estimation uses two frames as input whilst some recent methods consider multiple frames to …

Sun glint presents a significant challenge in marine ecological remote sensing by obscuring
valuable features of benthic communities, thus hindering accurate monitoring of these …

Camera-based object detection is integral to advanced driver assistance systems (ADAS)
and autonomous vehicle research, and RGB cameras remain indispensable for their spatial …

In recent years, many deep learning-based methods have been proposed to tackle the
problem of optical flow estimation and achieved promising results. However, they hardly …

Current deep learning-based phase unwrapping techniques for iToF Lidar sensors focus
mainly on static indoor scenarios, ignoring motion blur in dynamic outdoor scenarios. Our …

Single-frame optical flow estimation is a more challenging task than predicting the optical
flow between adjacent frames in a video. This paper presents a two-stream network that …

We propose a novel framework to generate clean video frames from a single motion-blurred
image. While a broad range of literature focuses on recovering a single image from a blurred …