Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution 26 Oct 2023 · Zhewei Huang, Ailin Huang, Xiaotao Hu, Chen Hu, Jun Xu, Shuchang Zhou · Edit social preview The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by...
MIT license YouTube|Poster|Enhancement Model|demo|中文介绍 Introduction We want to increase video resolution and frame rates end-to-end (end-to-end STVSR). This project is the implement ofScale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution. Our SAFA network outperform...
, the model pays more attention to contextual features. Secondly, the result of feature-based aggregation for each partition is obtained, and the four partition features are merged in the channel dimension. $$ F_{m}^{\prime} = \left[ {m_{1}^{\prime} ,m_{2}^{\prime} ,m_{3}^{...
To address these issues, we propose Feature-Adaptive FPN with Multiscale Context Integration (FA-FPN-MCI), a novel deep-learning algorithm aimed at enhancing both detection and domain generalization performance. We integrate the Style Normalization and Restitution (SNR) module for domain generalization...
First, we extract spatial feature maps based on different layers of CNN, so that our feature extractor can learn multi-scale semantic representations. Second, an attention-enhanced local adaptive aggregation learning strategies is designed to aggregate the spatial features of each scale. Not only the...
where reshape represents the dimension transformation of the output of MSAS to facilitate the compression aggregation of the FC layer, and the output result is (taking the values of 1, 2, 3, and 4 in this equation); represents the feature fusion operation; is the result of the feature ...
Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation a Multi-Scale Attentive Aggregation Network (MSAAN) to achieve the global consistency of point cloud feature representation and super segmentation performance... X Geng,S Ji,M Lu,... - 《Remote Sensing》 被引量: 0发表: 2021...
Multi-scale context aggregation by di- lated convolutions. In ICLR, 2016. [31] M. D. Zeiler, G. W. Taylor, and R. Fergus. Adaptive decon- volutional networks for mid and high level feature learning. In ICCV, 2011. [32] R. Zhang, S. Tang, M. Lin, J. Li, and S. Yan. ...
Firstly, since the backbone network continuously down-samples to extract image features, the size of the feature map is 1/32 of the original input size. While reducing the size of the feature map will reduce the amount of calculation, the spatial resolution of the feature map will also ...
Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2117–2125. [Google Scholar] Liu, S.; Qi, L.; Qin, H.; Shi, J.; Jia, J. Path aggregation network for instance ...