Chen Xiao, Jing Ruyun
School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, 210044, China.
Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, 210044, China.
Sci Rep. 2025 Mar 17;15(1):9050. doi: 10.1038/s41598-025-93758-z.
Video super resolution aims to generate high resolution video sequences from corresponding low resolution video sequences. Aiming at improving the insufficient utilization of temporal and spatial information of video sequences in current video super resolution methods, we proposed a new network based on deformable 3D convolutional group fusion. Input sequences were divided into groups according to different frame rates, which can effectively integrate time information in a hierarchical manner. The deformable 3D convolution was used for integration points within the good group of characteristics to keep the spatial and temporal correlation of video sequences. The introduction of time attention mechanism and group integration module provided supplementary information fusion for each group, to restore the missing details in the video sequence and generate high resolution video frames. Experimental results on Vid4 standard video data set show that The PSNR and SSIM of the generated high-resolution video frames are 27.39 and 0.8266, respectively. The network presented in this study has a good effect on the processing of motion video and has achieved better performance than current advanced methods.
视频超分辨率旨在从相应的低分辨率视频序列生成高分辨率视频序列。针对当前视频超分辨率方法中视频序列时空信息利用不足的问题，我们提出了一种基于可变形3D卷积组融合的新网络。输入序列根据不同帧率进行分组，能够有效地分层整合时间信息。可变形3D卷积用于在良好的特征组内进行积分点操作，以保持视频序列的时空相关性。引入时间注意力机制和组融合模块为每组提供补充信息融合，以恢复视频序列中缺失的细节并生成高分辨率视频帧。在Vid4标准视频数据集上的实验结果表明，生成的高分辨率视频帧的PSNR和SSIM分别为27.39和0.8266。本研究提出的网络在运动视频处理方面具有良好效果，并且比当前先进方法取得了更好的性能。
