Sorry, you need to enable JavaScript to visit this website.

Convolutional neural networks (CNN) have emerged as a powerful tool for solving computational imaging reconstruction problems. However, CNNs are generally difficult-to-understand black-boxes. Accordingly, it is challenging to know when they will work and, more importantly, when they will fail.

The relatively low resolution of Time-of-Flight (ToF) cameras, together with high power consumption and motion artifacts due to long exposure times, have kept ToF sensors away from classical lidar application fields, such as mobile robotics and autonomous driving. In this paper we note that while attempting to address the last two issues, e. g., via burst mode, the lateral resolution can be effectively increased. Differently from prior approaches, we propose a stripped-down modular super-resolution framework that operates in the raw data domain.

The relatively low resolution of Time-of-Flight (ToF) cameras, together with high power consumption and motion artifacts due to long exposure times, have kept ToF sensors away from classical lidar application fields, such as mobile robotics and autonomous driving. In this paper we note that while attempting to address the last two issues, e. g., via burst mode, the lateral resolution can be effectively increased. Differently from prior approaches, we propose a stripped-down modular super-resolution framework that operates in the raw data domain.

Change detection plays a vital role in monitoring and analyzing temporal changes in Earth observation tasks. This paper proposes a novel adaptive multi-scale and multi-level features fusion network for change detection in very-high-resolution bi-temporal remote sensing images. The proposed approach has three advantages. Firstly, it excels in abstracting high-level representations empowered by a highly effective feature extraction module.

High-level features can help low-level features eliminate semantic ambiguity, which is crucial for obtaining the precise salient object. Some methods use high-level features to pro vide global guidance for some layers of the network. However, there remain several problems: (1) the global guidance has not been fully mined, which leads to its limited capacity; (2) the semantic gap between global guidance and lowlevel features is ignored, and simple merging methods will cause feature aliasing.

Network pruning can be achieved by removing redundant channels. In this paper, we regard a channel ‘redundant’ if its output is linearly dependent with respect to those of other channels. Inspired by this, we propose an efficient pruning method, named as LDFM, by linear dependency analysis on all the feature maps of each individual layer.

High-level features can help low-level features eliminate semantic ambiguity, which is crucial for obtaining the precise salient object. Some methods use high-level features to pro vide global guidance for some layers of the network. However, there remain several problems: (1) the global guidance has not been fully mined, which leads to its limited capacity; (2) the semantic gap between global guidance and lowlevel features is ignored, and simple merging methods will cause feature aliasing.