Filters








9 Hits in 1.7 sec

Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation [article]

Mengyu Chu, You Xie, Jonas Mayer, Laura Leal-Taixé, Nils Thuerey
2019 arXiv   pre-print
This is crucial for sequential generation tasks, e.g. video super-resolution and unpaired video translation.  ...  We focus on temporal self-supervision for GAN-based video generation tasks.  ...  ACKNOWLEDGEMENTS This work was supported by the ERC Starting Grant realFlow (StG-2015-637014), and we would like to thank Kiwon Um for helping with the user studies.  ... 
arXiv:1811.09393v3 fatcat:ogcpqymcxnafnktgf2dtfpxdba

A multiresolution mixture generative adversarial network for video super-resolution

Zhiqiang Tian, Yudiao Wang, Shaoyi Du, Xuguang Lan, You Yang
2020 PLoS ONE  
for video super-resolution (MRMVSR).  ...  Generative adversarial networks (GANs) have been used to obtain super-resolution (SR) videos that have improved visual perception quality and more coherent details.  ...  However, using adversarial training for video super-resolution (VSR) has not received the same attention.  ... 
doi:10.1371/journal.pone.0235352 pmid:32649694 fatcat:5pam5g32pzcajh7dft7rasmnya

Real-Time Super-Resolution System of 4K-Video Based on Deep Learning [article]

Yanpeng Cao, Chengcheng Wang, Changjun Song, Yongming Tang, He Li
2021 arXiv   pre-print
The proposed EGVSR is based on spatio-temporal adversarial learning for temporal coherence.  ...  Video super-resolution (VSR) technology excels in reconstructing low-quality video, avoiding unpleasant blur effect caused by interpolation-based algorithms.  ...  Evalution of Video Quality and Temporal Coherence In this section, we will investigate the objective evaluation of video quality for our VSR system.  ... 
arXiv:2107.05307v2 fatcat:5fxhco3mtfgwzoukazgwvpfhxu

Video Super-Resolution Based on Generative Adversarial Network and Edge Enhancement

Jialu Wang, Guowei Teng, Ping An
2021 Electronics  
In this paper, we proposed a model based on Generative Adversarial Network (GAN) and edge enhancement to perform super-resolution (SR) reconstruction for LR and blur videos, such as closed-circuit television  ...  With the help of deep neural networks, video super-resolution (VSR) has made a huge breakthrough. However, these deep learning-based methods are rarely used in specific situations.  ...  video super-resolution [43] and TecoGAN means temporally coherent generative adversarial network [46] .  ... 
doi:10.3390/electronics10040459 fatcat:yxtcx7s7wjf73fn7ehu2rwy7hy

Learning the Loss Functions in a Discriminative Space for Video Restoration [article]

Younghyun Jo, Jaeyeon Kang, Seoung Wug Oh, Seonghyeon Nam, Peter Vajda, Seon Joo Kim
2020 arXiv   pre-print
In addition, we also introduce a new relation loss in order to maintain the temporal consistency in output videos.  ...  With more advanced deep network architectures and learning schemes such as GANs, the performance of video restoration algorithms has greatly improved recently.  ...  For comparisons, we choose EnhanceNet [29] (GAN based single-image super-resolution), EDVR [38] (pixel loss only), and TecoGAN [7] (GAN based video super-resolution).  ... 
arXiv:2003.09124v1 fatcat:2b53t4cawrb5pb622qqkyddrri

A comparative study of various Deep Learning techniques for spatio-temporal Super-Resolution reconstruction of Forced Isotropic Turbulent flows [article]

T.S.Sachin Venkatesh, Rajat Srivastava, Pratyush Bhatt, Prince Tyagi, Raj Kumar Singh
2021 arXiv   pre-print
spatial and temporal super-resolution of turbulent flow fields.  ...  This study performs super-resolution analysis on turbulent flow fields spatially and temporally using various state-of-the-art machine learning techniques like ESPCN, ESRGAN and TecoGAN to reconstruct  ...  We would also like to thank other members of the Fluid Mechanics Group for directly or indirectly helping during the research work.  ... 
arXiv:2107.03361v1 fatcat:okltzsj6uzer3em2hcectjyxzq

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
2020 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.  ...  FSTRN Fig. 12 : The network architecture of TecoGAN [27] . 9) TecoGAN: Temporally coherent GAN (TecoGAN) 6 [27] mainly proposes a spatio-temporal discriminator for realistic and coherent video super-resolution  ... 
arXiv:2007.12928v2 fatcat:dmyyejwuf5b27dxaqlj6pfari4

Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation [article]

Jiaming Liu, Ming Lu, Kaixin Chen, Xiaoqi Li, Shizun Wang, Zhaoqing Wang, Enhua Wu, Yurong Chen, Chuang Zhang, Ming Wu
2021 arXiv   pre-print
These methods divide a video into chunks, and stream LR video chunks and corresponding content-aware models to the client. The client runs the inference of models to super-resolve the LR chunks.  ...  carefully study the relation between models of different chunks, then we tactfully design a joint training framework along with the Content-aware Feature Modulation (CaFM) layer to compress these models for  ...  TecoGAN [5] explores the temporal self-supervision for GAN-based VSR.  ... 
arXiv:2108.08202v2 fatcat:eax5p7gxfbgc3ltlkgo2vqly2a

Multi-Frame Labeled Faces Database: Towards Face Super-Resolution from Realistic Video Sequences

Martin Rajnoha, Anzhelika Mezina, Radim Burget
2020 Applied Sciences  
This paper also introduces a new multi-frame face super-resolution method and compares this method with the state-of-the-art single-frame and multi-frame super-resolution methods.  ...  Forensically trained facial reviewers are still considered as one of the most accurate approaches for person identification from video records.  ...  TecoGAN [27] is the architecture proposed to solve the following video generation tasks: Video super-resolution (VSR) and Unpaired Video Translation (UVT).  ... 
doi:10.3390/app10207213 fatcat:wtjztnvxmzch7i3fnagnugugla