Super-resolution (SR) is an effective approach to enhance image spatial resolution. Although many SR algorithms have been proposed by far, little progress has been made to improve resolution for a noisy image. Conventional approaches always adopt the denoising step before applying the SR method to noisy low-resolution images. However, some high-frequency details lose during the denoising step and cannot be restored by the following SR step. Therefore, motivated by the success of deep learning in different computer vision missions, we propose a novel method named Denoising Super-Resolution Deep Convolutional Network (DSR-DCN), to combine both denoising and SR step in a single deep model. The proposed deep model straightly learns an end-to-end mapping from noisy LR space to the corresponding HR space. To equip the proposed network with the capability of blind denoising, Gaussian noise, with a range of standard deviation instead of constant value, is added to each patch of the LR space during training. Experiment results demonstrate that DSR-DCN achieves superior performance and better visual effects than the conventional approaches.
Error floor behavior of low-density parity-check (LDPC) codes using quantized decoding algorithms is statistically
studied with experimental results on a hardware evaluation platform. The results present the distribution of the residual
errors after decoding failure and reveal that the number of residual error bits in a codeword is usually very small using
quantized sum-product (SP) algorithm. Therefore, LDPC code may serve as the inner code in a concatenated coding
system with a high code rate outer code and thus an ultra low error floor can be achieved. This conclusion is also verified
by the experimental results.
Joint source-channel coding schemes have been proven to be effective ways for reliable multimedia communications. In this paper, a joint source-channel decoding (JSCD) scheme that combines the hidden Markov source (HMS) estimation and low-density parity-check (LDPC) coding is proposed for the standard MPEG-2 video transmission. The LDPC code of the proposed scheme has a near-Shannon-limit error-correcting capability, while the HMS estimator may accurately extract the residual redundancy within the MPEG-2 video stream without any prior information. Furthermore, with a joint iterative decoding algorithm, the estimated source redundancy may be well exploited by the LDPC decoder, and the channel decoding feedback may refine the subsequence HMS estimation, thereby effectively improving the system performance. On the other hand, we also show that the proposed JSCD scheme has approximately the same computation complexity as that of the standard decoding scheme. Moreover, it is worth noting that the proposed scheme is based on separation encoding schemes, which is very convenient to be applied to existing multimedia transmission systems.