In this paper, we propose a robust and efficient end-to-end non-local spatial propagation
network for depth completion. The proposed network takes RGB and sparse depth images …

We present a general learning-based solution for restoring images suffering from spatially-
varying degradations. Prior approaches are typically degradation-specific and employ the …

The current superresolution (SR) methods based on deep learning have shown remarkable
comparative advantages but remain unsatisfactory in recovering the high-frequency edge …

Camera sensors often fail to capture clear images or videos in a poorly lit environment. In
this paper, we propose a trainable hybrid network to enhance the visibility of such degraded …

Performance is a critical challenge in mobile image processing. Given a reference imaging
pipeline, or even human-adjusted pairs of images, we seek to reproduce the enhancements …

Semantic image inpainting is a challenging task where large missing regions have to be
filled based on the available visual data. Existing methods which extract information from …

Due to the spatially variant blur caused by camera shake and object motions under different
scene depths, deblurring images captured from dynamic scenes is challenging. Although …

We present an approach to accelerating a wide variety of image processing operators. Our
approach uses a fully-convolutional network that is trained on input-output pairs that …

Depth completion aims to recover a dense depth map from the sparse depth data and the
corresponding single RGB image. The observed pixels provide the significant guidance for …

Deep learning has recently been applied with impressive results to extreme low-light
imaging. Despite the success of single-image processing, extreme low-light video …