SC-HVPPNet: Spatial and Channel Hybrid-Attention Video Post-Processing Network with CNN and Transformer

arXiv:2404.14709v1 Announce Type: new
Abstract: Convolutional Neural Network (CNN) and Transformer have attracted much attention recently for video post-processing (VPP). However, the interaction between CNN and Transformer in existing VPP methods is not fully explored, leading to inefficient communication between the local and global extracted features. In this paper, we explore the interaction between CNN and Transformer in the task of VPP, and propose a novel Spatial and Channel Hybrid-Attention Video Post-Processing Network (SC-HVPPNet), which can cooperatively exploit the image …

abstract arxiv attention cnn communication convolutional neural network cs.cv eess.iv features global however hybrid network neural network post-processing processing spatial transformer type video