7 Hits in 1.9 sec

3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks [article]

Soo Ye Kim, Jeongyeon Lim, Taeyoung Na, Munchurl Kim
2019 arXiv   pre-print
To this end, we propose an effective 3D-CNN for video super-resolution, called the 3DSRnet that does not require motion alignment as preprocessing.  ...  Although 2D convolutional neural networks (CNNs) are powerful in modelling images, 3D-CNNs are more suitable for spatio-temporal feature extraction as they can preserve temporal information.  ...  Video Super-resolution Subnet 3.1.1 3D Convolution Layers.  ... 
arXiv:1812.09079v2 fatcat:ud4j5vsuqfgxbjodkhuvbu32xe

Satellite Image Multi-Frame Super Resolution Using 3D Wide-Activation Neural Networks

Francisco Dorr
2020 Remote Sensing  
The model is based on proven methods that worked on 2D images tweaked to work on 3D: the Wide Activation Super Resolution (WDSR) family.  ...  Deep learning approaches to Super Resolution (SR) reached the state-of-the-art in multiple benchmarks; however, most of them were studied in a single-frame fashion.  ...  [19] for video super resolution: 3DSRnet. They used a 3D-CNN that takes five low-resolution input frames and seeks to increase the resolution of the middle frame.  ... 
doi:10.3390/rs12223812 fatcat:qekvdmejgvdoddmkxziafpjgja

Video Super Resolution Based on Deep Learning: A Comprehensive Survey [article]

Hongying Liu, Zhubo Ruan, Peng Zhao, Chao Dong, Fanhua Shang, Yuanyuan Liu, Linlin Yang, Radu Timofte
2022 arXiv   pre-print
It is well known that the leverage of information within video frames is important for video super-resolution.  ...  In this survey, we comprehensively investigate 33 state-of-the-art video super-resolution (VSR) methods based on deep learning.  ...  2019a) CVPR 2019 Fast Spatio-Temporal Residual Network for Video Super-Resolution 3D Conv Cb loss × 3DSRnet (Kim et al., 2019) ICIP 2019 3D Super-Resolution Network MSE loss × DSMC (Liu et al., 2021a)  ... 
arXiv:2007.12928v3 fatcat:nxoejcfdnzas3jznbqsale36ty

Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling [article]

Hongying Liu, Peng Zhao, Zhubo Ruan, Fanhua Shang, Yuanyuan Liu
2021 arXiv   pre-print
In this paper, we propose a novel deep neural network with Dual Subnet and Multi-stage Communicated Upsampling (DSMC) for super-resolution of videos with large motion.  ...  Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR).  ...  Introduction Video super-resolution (VSR) aims at recovering the corresponding high-resolution (HR) counterpart from a given low-resolution (LR) video (Liu et al. 2020b) .  ... 
arXiv:2103.11744v1 fatcat:33rwxdijybgffamponryrx2lqm

A Novel Dual Dense Connection Network for Video Super-resolution [article]

Guofang Li, Yonggui Zhu
2022 arXiv   pre-print
Video super-resolution (VSR) refers to the reconstruction of high-resolution (HR) video from the corresponding low-resolution (LR) video. Recently, VSR has received increasing attention.  ...  In this paper, we propose a novel dual dense connection network that can generate high-quality super-resolution (SR) results.  ...  Conclusion In this paper, we present a novel video super-resolution network which utilize densely connected convolutional network in both inner and outer layers.  ... 
arXiv:2203.02723v1 fatcat:nbbj7b3chveg3bqtz5thonx4xi

A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-Resolution [article]

Hongying Liu, Zhubo Ruan, Chaowei Fang, Peng Zhao, Fanhua Shang, Yuanyuan Liu, Lijun Wang
2020 arXiv   pre-print
In this paper, we propose a novel single frame and multi-frame joint network (SMFN) for recovering high-resolution spherical videos from low-resolution inputs.  ...  This is the first attempt to settle the super-resolution of spherical videos, and we collect a novel dataset from the Internet, MiG Panorama Video, which includes 204 videos.  ...  (FFCVSR) [40] , and the 3D super-resolution network (3DSRNet) [41] .  ... 
arXiv:2008.10320v1 fatcat:un7amaq52zfvhasxyned24jvv4

An overview of video super-resolution algorithms

C. Liu, R. Gang, J. Li, J. Fang, Haodong Yu
We investigate some excellent algorithms in the field of video space super-resolution based on artificial intelligence, structurally analyze the network structure of the algorithm and the commonly used  ...  We also analyze the characteristics of algorithms in the new field of video space-time super-resolution.  ...  At present, the video spatio-temporal super-resolution model is mainly composed of basic structures such as 3D convolution and Recurrent Convolutional Neural Network (RCNN).  ... 
doi:10.5445/ir/1000139918 fatcat:czgh4jkkwjhxve7l73gtdpp65m