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

In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos.

Recently, the PnP-GAP algorithm has achieved remarkable reconstruction quality for snapshot compressive imaging (SCI), and its convergence has been proven based on the condition of diminishing noise levels and the assumption of

Recently, the PnP-GAP algorithm has achieved remarkable reconstruction quality for snapshot compressive imaging (SCI), and its convergence has been proven based on the condition of diminishing noise levels and the assumption of

In this paper, a deep learning network with double closed- loop structure is introduced to tackle the image deblurring problem. The first closed-loop in our model is composed of two networks which learn a pair of opposite mappings between the blurry and sharp images. By this way, the solution spaces of possible functions that map a blurry image to its sharp counterpart can be effectively reduced. Furthermore, the first closed-loop also helps our model to deal with the unpaired samples in the training set.

We study the problem of efficiently summarizing a short video into several keyframes, leveraging recent progress in fast graph sampling. Specifically, we first construct a similarity path graph (SPG) $\cG$, represented by graph Laplacian matrix $\L$, where the similarities between adjacent frames are encoded as positive edge weights. We show that maximizing the smallest eigenvalue $\lambda_{\min}(\B)$ of a coefficient matrix $\B = \text{diag}(\a) + \mu \L$, where $\a$ is the binary keyframe selection vector, is equivalent to minimizing a worst-case signal reconstruction error.

Compressed sensing (CS), a popular signal processing technique, can achieve compression and encryption simultaneously. Therefore, it has extension applications in various fields. However, CS is vulnerable to cryptographic attacks for its linear encoding process. To solve this problem, a permutation-diffusion structure is designed and embedded to the CS encoding process. In addition, it can increase the key space while compressing. Since the permutation-diffusion structure reduces the sparseness, superior recovery performance cannot be achieved.

The existing low-light image enhancement methods may cause under enhancement, unbalanced brightness and blurriness. To address these shortcomings, we proposed the non-linear mapping method based on the Retinex theory (NMMR). We use an improved traditional gamma function to estimate the reflectance, and we proposed the maximum brightness channel to estimate the illumination.

Video post-processing is a method to improve the quality of reconstructed frames at the
decoder side. Although the existing post-processing algorithms based on deep learning
can achieve signicant quality improvement compared with traditional methods, they will
require a lot of computational resources, which makes these algorithms difficult to use
on mobile devices. To tackle this problem, a low-complexity neural network based on
max-pooling and depth-wise separable convolution is proposed in this work for compressed