Congrui Fu

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. Our method combines long-term global information and short-term local information from the video to better extract complete and accurate spatial-temporal information. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This provides a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms open source state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.2 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectively), and visual quality.

Screen content (SC) differs from natural scene (NS) with unique characteristics such as noise-free, repetitive patterns, and high contrast. Aiming at addressing the inadequacies of current learned image compression (LIC) methods for SC, we propose an improved two-stage octave convolutional residual blocks (IToRB) for high and low-frequency feature extraction and a cascaded two-stage multi-scale residual blocks (CTMSRB) for improved multi-scale learning and nonlinearity in SC. Additionally, we employ a window-based attention module (WAM) to capture pixel correlations, especially for high contrast regions in the image. We also construct a diverse SC image compression dataset (SDU-SCICD2K) for training, including text, charts, graphics, animation, movie, game and mixture of SC images and NS images. Experimental results show our method, more suited for SC than NS data, outperforms existing LIC methods in rate-distortion performance on SC images. The code is publicly available at https://github.com/SunshineSki/OMR Net.git.

Screen content (SC) differs from natural scene (NS) with unique characteristics such as noise-free, repetitive patterns, and high contrast. Aiming at addressing the inadequacies of current learned image compression (LIC) methods for SC, we propose an improved two-stage octave convolutional residual blocks (IToRB) for high and low-frequency feature extraction and a cascaded two-stage multi-scale residual blocks (CTMSRB) for improved multi-scale learning and nonlinearity in SC. Additionally, we employ a window-based attention module (WAM) to capture pixel correlations, especially for high contrast regions in the image. We also construct a diverse SC image compression dataset (SDU-SCICD2K) for training, including text, charts, graphics, animation, movie, game and mixture of SC images and NS images. Experimental results show our method, more suited for SC than NS data, outperforms existing LIC methods in rate-distortion performance on SC images. The code is publicly available at https://github.com/SunshineSki/OMR Net.git

Joint space-time video super-resolution aims to increase both the spatial resolution and the frame rate of a video sequence. As a result, details become more apparent, leading to a better and more realistic viewing experience. This is particularly valuable for applications such as video streaming, video surveillance (object recognition and tracking), and digital entertainment. Over the last few years, several joint space-time video super-resolution methods have been proposed. While those built on deep learning have shown great potential, their performance still falls short. One major reason is that they heavily rely on two-dimensional (2D) convolutional networks, which restricts their capacity to effectively exploit spatio-temporal information. To address this limitation, we propose a novel generative adversarial network for joint space-time video super-resolution. The novelty of our network is twofold. First, we propose a three-dimensional (3D) attention mechanism instead of traditional two-dimensional attention mechanisms. Our generator uses 3D convolutions associated with the proposed 3D attention mechanism to process temporal and spatial information simultaneously and focus on the most important channel and spatial features. Second, we design two discriminator strategies to enhance the performance of the generator. The discriminative network uses a two-branch structure to handle the intra-frame texture details and inter-frame motion occlusions in parallel, making the generated results more accurate. Experimental results on the Vid4, Vimeo-90 K, and REDS datasets demonstrate the effectiveness of the proposed method.

Inter prediction is a crucial part of hybrid video coding frameworks, and it is used to eliminate redundancy in adjacent frames and improve coding performance. During inter prediction, motion estimation is used to find the reference block that is most similar to the current block, and the following motion compensation is used to shift the reference block fractionally to obtain the prediction block. The closer the reference block is to the original block, the higher the coding efficiency is. To improve the quality of reference blocks, a quality enhancement network (RBENN) that is dedicated to reference blocks is proposed. The main body of the network consists of 10 residual modules, with two convolution layers for preprocessing and feature extraction. Each residual module consists of two convolutional layers, one ReLU activation, and a shortcut. The network uses the luma reference block as input before motion compensation, and the enhanced reference block is then filtered by the default fractional interpolation. Moreover, the proposed method can be used for both conventional motion compensation and affine motion compensation. Experimental results showed that RBENN could achieve a −1.35% BD rate on average under the low-delay P (LDP) configuration compared with the latest H.266/VVC.