24 August 2018 in IEEE Transactions on Circuits and Systems for Video Technology
Multiple description coding (MDC) is able to stably transmit signal in un-reliable and non-prioritized networks, which has been broadly studied for several decades. However, traditional MDC doesn’t well leverage image’s context features to generate multiple descriptions. In this paper, we propose a novel standard-compliant convolutional neural network-based MDC framework, which efficiently leverages image’s context information to compress image. Firstly, multiple description generator network (MDGN) is designed to produce appearance-similar yet feature-different multiple descriptions automatically according to image’s content, which are compressed by standard codec. Secondly, we present multiple description reconstruction network (MDRN) including side reconstruction networks (SRN) and central reconstruction network (CRN). When any one of two lossy descriptions is received at decoder, SRN network is used to improve the quality of this decoded lossy description by simultaneously removing compression artifact and up-sampling. Meanwhile, we utilize CRN network with two decoded descriptions as inputs for better reconstruction, if both of lossy descriptions are available. Thirdly, multiple description virtual codec network (MDVCN) is proposed to bridge the gap between MDGN network and MDRN network in order to train an end-to-end MDC framework. Here, two learning algorithms are provided to train our whole framework. In addition to structural dis-similarity loss function, the produced descriptions are used as opposing labels with multiple description distance loss function to regularize the training of MDGN network. These losses guarantee that the generated descriptions are structurally similar yet finely diverse. Experimental results show a great deal of objective and subjective quality measurements to validate the effectiveness of our framework.
1 July 2024 in IEEE Transactions on Computational Imaging
Low contrast, noise pollution and color distortion of low-light images tremendously affect human visual perception. The Retinex and its variant models are widely used for low-light image enhancement (LLIE). However, the performances of traditional Retinex algorithms are limited by intrinsic non-learnable characteristic. Recently, the latest LLIE methods directly unfold Retinex model as the popular networks such as URetinex-Net and RAUNA to resolve the black-box problem of conventional neural networks. Different from these methods focusing on the unfolding of image decomposition, we treat the classic LLIE as an image reconstruction task. Built upon Retinex theory, we propose a Retinex-Inspired Reconstruction Optimization (RIRO) model, which is unrolled as the RIRO network. This network consists of Low-light Decomposition and Enhancement Sub-Network (LDE Sub-Net) and Image Reconstruction Unrolling Sub-Network (IRU Sub-Net). The LDE Sub-Net is leveraged for the input initialization of the IRU Sub-Net. In RIRO model, we introduce a Dual-Domain Proximal (DDP) block to replace classic proximal operator, in which Fourier transform is utilized to transform spatial domain information into frequency domain information so as to simultaneously extract dual features on both spatial and frequency domains. Besides, we design a residual-aware weighted dual-fusion module and an adaptive weighted triple-fusion module to fuse different kinds of features. Numerous experiments on benchmark datasets have shown that the proposed method outperforms many advanced LIE methods. Our codes are publicly released at here.
1 June 2023 in Knowledge-Based Systems
1 February 2015 in Electronics Letters
In three‐dimensional (3D) video, a compressed depth map usually has large distortions along‐boundaries, leading to object deformation and artefacts in synthesised views. A so‐called candidate values based boundary filtering (CVBF) with low computational complexity by filtering only some detected unreliable pixels along the boundaries is proposed. Assuming that the smooth regions consist of reliable pixels, CVBF selects an appropriate candidate value to replace each unreliable pixel based on both the nearest reliable pixels and the mean values of surrounding regions. Experimental results show that synthesised views with CVBF‐filtered depth maps are better than existing joint trilateral filtering, the depth boundary reconstruction filter and the adaptive depth truncation filter.
16 December 2022 in Pattern Recognition
27 June 2025 in Pattern Recognition