Guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution
depth map from a low-resolution observation with the help of a paired high-resolution color …

Dense depth perception is critical for autonomous driving and other robotics applications.
However, modern LiDAR sensors only provide sparse depth measurement. It is thus …

Depth boundaries often lose sharpness when upsampling from low-resolution (LR) depth
maps especially at large upscaling factors. We present a new method to address the …

We present the bilateral solver, a novel algorithm for edge-aware smoothing that combines
the flexibility and speed of simple filtering approaches with the accuracy of domain-specific …

Image processing and pixel-wise dense prediction have been advanced by harnessing the
capabilities of deep learning. One central issue of deep learning is the limited capacity to …

This work addresses the problem of semantic scene understanding under dense fog.
Although considerable progress has been made in semantic scene understanding, it is …

In this paper, we propose a novel deep convolutional neural network to solve the general
multi-modal image restoration (MIR) and multi-modal image fusion (MIF) problems. Different …

Joint image filters can leverage the guidance image as a prior and transfer the structural
details from the guidance image to the target image for suppressing noise or enhancing …

Local windows are routinely used in computer vision and almost without exception the
center of the window is aligned with the pixels being processed. We show that this …

Joint image filters leverage the guidance image as a prior and transfer the structural details
from the guidance image to the target image for suppressing noise or enhancing spatial …