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

One of the most critical missions of sonar is to capture deep-sea pictures to depict sea floor and various objects, and provide an immense understanding of biology and geology in deep sea. Due to the poor condition of underwater acoustic channel, the captured sonar images very possibly suffer from several typical types of distortions before finally reaching to users. Unfortunately, very limited efforts have been devoted to collecting meaningful sonar image databases and benchmark reliable objective quality predictors.

Among image enhancement methods, histogram equalization (HE) has received the most attention because of its intuitive implementation quality, high efficiency, and the monotonicity of its intensity mapping function. However, HE is indiscriminate and overemphasizes the contrast around intensities with large pixel populations but little visual importance. To address this issue, we propose an HE-based method that adaptively controls the contrast gain according to the potential visual importance of intensities and pixels.

Depth maps captured by RGB-D cameras are often noisy and incomplete at edge regions. Most existing methods assume that there is a co-occurrence of edges in depth map and its corresponding color image, and improve the quality of depth map guided by the color image. However, when the color image is noisy or richly detailed, the high frequency artifacts will be introduced into depth map. In this paper, we propose a deep residual network based on deep fusion and local linear regularization for guided depth enhancement.

Visual context has formed a robust stimulation for visual perception. Spatio-temporal context in existing trackers sometimes shows weak reliability in visible light videos with poor quality. Supplemented by the infrared perception, this work exploits the role of visual context in tracking in a spatial-sequential-spectral view, by which to excavate dominance of different contexts in various scenarios.

In motion compensated frame interpolation, a repetition
pattern in an image makes it difficult to derive an accurate
motion vector because multiple similar local minima exist in
the search space of the matching cost for motion estimation.
In order to improve the accuracy of motion estimation in a
repetition region, this paper attempts a semi-global approach
that exploits both local and global characteristics of a
repetition region. Experimental results demonstrate that the
proposed method significantly outperforms the previous local

Image-set classification has recently generated great popularity due to widespread application to challenging tasks in computer vision. The great challenges arise from measuring the similarity between image sets which usually exhibit huge inter-class ambiguity and intra-class variation. In this paper, based on the assumption that each image set as a linear subspace can be treated as a point on a Grassmann manifold, we propose discriminant Grassmann kernels (DGK) of principal angles between subspaces.