The success of convolutional neural network (CNN) based single image dynamic scene blind deblurring (SIDSBD) methods mainly stems from the multi-scale/multi-patch model and the designs of the encoder-decoder architecture, and the residual block structure, which make different contributions to SIDSBD. In this paper, we further exploit the advantages of the multi-scale model, the encoder-decoder module, and the residual block structure, respectively, and propose a novel multi-scale channel attention network (MSCAN) for effective single image dynamic scene blind deblurring. Different from existing multi-scale models, in our proposed network, each scale consists of multiple levels, in which a novel spatial pyramid pooling channel attention (SPPCA) strategy is proposed to adaptively rescale the channel-wise features by using both the global and local feature statistics for more powerful network representation. Extensive experiments on both the synthetic benchmark datasets and the real blurred images show that our method can produce better deblurring results than the state-of-the-art SIDSBD methods in terms of both qualitative evaluation and quantitative metrics.

Versatile Video Coding (VVC) significantly improves the coding efficiency over the preceding high efficiency video coding (HEVC) standard, but at the expense of much higher computational complexity. Specifically for intra coding of VVC, the computational burden is mainly on the brute-force recursive rate-distortion optimization (RDO) search of quadtree with nested multi-type tree (QTMT) based coding unit (CU) partition structure. Consequently, we propose a random forest based algorithm to reduce the complexity of CU partition. The CUs are first divided into three categories, namely simple, fuzzy, and complex CUs. For simple and complex CUs, one random forest classifier is trained to directly predict the optimal partition mode. For fuzzy CUs, another random forest is trained to predict whether the partition process is terminated or not. The experimental results show that the complexity reduction of the proposed algorithm is up to 69% as compared to the VVC reference software (VTM 7.0), and averagely 57% encoding time saving is achieved with 1.21 % BDBR increase.

Recently, a novel uncoded (pseudo-analog) scheme called SoftCast is proposed for wireless video transmission, which eliminates the cliff effect of the state-of-the-art source-channel coding based scheme and achieves linear quality transition within a wide range of channel Signal-to-Noise Ratio (SNR). Therefore, SoftCast-like uncoded and hybrid transmission has become an attractive research issue for natural two-dimensional (2D) video. However, very few studies focus on the SoftCast based wireless transmission of the three-dimensional video (3DV) currently. One critical issue of 3DV SoftCast is how to allocate the limited power budget of the transmitter to the texture videos and depth maps of the 3DV to achieve the optimal overall quality on the receiver side, including the transmission quality of the reference views and the synthesis quality of the virtual views. This paper attempts to solve the optimal joint power allocation problem in an efficient way. First, we formulate the target problem as a constrained power-distortion optimization (PDO) problem mathematically. Then, each part of the distortion is analyzed and formulated in a closed-form. Finally, the PDO problem is mapped to an unconstrained convex optimization problem and solved by Lagrangian multiplier method. Simulation results demonstrate that the performance of the proposed method is close to that of the full search method, which can provide the best performance theoretically. Nevertheless, the complexity of the proposed method is negligible as compared to that of the full search method. In addition, as compared with the fixed ratio (e.g., 1:1) power allocation between texture and depth, the proposed method can achieve a PNSR gain up to 1.8dB.

Previous studies have shown that temporally dependent rate-distortion optimization (RDO) methods can enhance the compression performance of video encoders. However, accurately quantifying temporal rate-distortion dependencies in the latest video coding standard, Versatile Video Coding (VVC), remains a significant challenge. To address this issue, this paper proposes a distortion propagation factor (DPF) estimation method tailored for VVC low-delay hierarchical coding, aiming to achieve temporally dependent RDO. Specifically, we first derive a formula for calculating the DPF based on coding distortion and motion-compensated prediction (MCP) errors. Building on this, we present several pre-encoding-based DPF estimation schemes designed for the VVC low-delay hierarchical coding structure. These schemes have very low computational complexity and do not require buffering subsequent unencoded frames for pre-analysis, thereby avoiding additional encoding delays. Finally, the estimated DPFs are used to adaptively adjust the Lagrange multipliers and quantization parameters of each coding tree unit, optimizing the allocation of coding bit resources. After integrating the proposed method into the VVC test model VTM-23.0, experimental results show that one of the proposed DPF estimation schemes achieves average bit rate savings of 4.25% for low-delay B slices and 4.12% for low-delay P slices, with only a 1% increase in computational complexity. The proposed method offers an effective solution for enhancing the compression performance of VVC encoders. Consequently, the proposed DPF estimation approaches have already been adopted by the Joint Video Experts Team (JVET) and officially integrated into the VVC reference software.