Filters








20 Hits in 5.9 sec

NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results [article]

Ren Yang, Radu Timofte, Meisong Zheng, Qunliang Xing, Minglang Qiao, Mai Xu, Lai Jiang, Huaida Liu, Ying Chen, Youcheng Ben, Xiao Zhou, Chen Fu (+67 others)
2022 arXiv   pre-print
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video.  ...  The proposed methods and solutions gauge the state-of-the-art of super-resolution and quality enhancement of compressed video.  ...  We also thank Peilin Chen and Prof. Shiqi Wang from the City University of Hong Kong for providing the results of their method [13] on the validation and test sets.  ... 
arXiv:2204.09314v2 fatcat:br5dapahr5cyrjowcfjwlkkdnm

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
In this survey, we comprehensively investigate 33 state-of-the-art video super-resolution (VSR) methods based on deep learning.  ...  Finally, we summarize and compare the performance of the representative VSR method on some benchmark datasets.  ...  Zekun Li (Master student at School of Artificial Intelligence in Xidian University) and Dr.  ... 
arXiv:2007.12928v3 fatcat:nxoejcfdnzas3jznbqsale36ty

Deep Neural Network–based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions

Royson Lee, Stylianos I. Venieris, Nicholas D. Lane
2022 ACM Computing Surveys  
In recent years, advances in the field of deep learning on tasks such as super-resolution and image enhancement have led to unprecedented performance in generating high-quality images from low-quality  ...  Internet-enabled smartphones and ultra-wide displays are transforming a variety of visual apps spanning from on-demand movies and 360° videos to video-conferencing and live streaming.  ...  Another recent key method that enables tackling this challenge in general is neural enhancement through super-resolution (SR) and image enhancement models.  ... 
doi:10.1145/3469094 fatcat:vonlsk72hbg27jx2q6umrfpu2q

Deep Learning Approaches for Video Compression: A Bibliometric Analysis

Ranjeet Bidwe, Sashikala Mishra, Shruti Patil, Kailash Shaw, Deepali Vora, Ketan Kotecha, Bhushan Zope
2022 Big Data and Cognitive Computing  
The qualitative analysis provides information on DL-based approaches for video compression, as well as the advantages, disadvantages, and challenges of using them.  ...  This paper presents a bibliometric analysis and literature survey of all Deep Learning (DL) methods used in video compression in recent years.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/bdcc6020044 fatcat:w3hsnm4c6fantctozkwio5qklu

Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling [article]

Takashi Isobe and Xu Jia and Xin Tao and Changlin Li and Ruihuang Li and Yongjie Shi and Jing Mu and Huchuan Lu and Yu-Wing Tai
2022 arXiv   pre-print
Experiments on several video super-resolution benchmark datasets demonstrate the effectiveness of the proposed method and its favorable performance against state-of-the-art methods.  ...  Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation.  ...  The quantitative results of the stateof-the-art methods are shown in Table 3 . ETDM achieves a good balance between speed and reconstruction quality on these datasets.  ... 
arXiv:2204.07114v1 fatcat:sfq4luziwrhxzaqfe5wrzndwcq

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results [article]

Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Richard Shaw, Aleš Leonardis, Radu Timofte, Zexin Zhang, Cen Liu, Yunbo Peng, Yue Lin, Gaocheng Yu, Jin Zhang, Zhe Ma (+81 others)
2022 arXiv   pre-print
This manuscript focuses on the competition set-up, datasets, the proposed methods and their results.  ...  This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022  ...  Acknowledgments We thank the NTIRE 2022 sponsors: Huawei, Reality Labs, Bending Spoons, MediaTek, OPPO, Oddity, Voy-age81, ETH Zürich (Computer Vision Lab) and University of Würzburg (CAIDAS).  ... 
arXiv:2205.12633v1 fatcat:2qrfaoxxgzcrhg7jbugu35b5yq

Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network [article]

Shanshan Lao, Yuan Gong, Shuwei Shi, Sidi Yang, Tianhe Wu, Jiahao Wang, Weihao Xia, Yujiu Yang
2022 arXiv   pre-print
The experiments show that our model outperforms the state-of-the-art methods on four standard IQA datasets and AHIQ ranked first on the Full Reference (FR) track of the NTIRE 2022 Perceptual Image Quality  ...  Therefore, we propose an Attention-based Hybrid Image Quality Assessment Network (AHIQ) to deal with the challenge and get better performance on the GAN-based IQA task.  ...  We compare our models with the state-of-the-art FR-IQA methods on the NTIRE 2022 IQA challenge validation and testing datasets.  ... 
arXiv:2204.10485v1 fatcat:x42xnvz6crdtdhnrxtmouc3irm

Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric [article]

Eugene Lyapustin, Anastasia Kirillova, Viacheslav Meshchaninov, Evgeney Zimin, Nikolai Karetin, Dmitriy Vatolin
2022 arXiv   pre-print
Super-resolution (SR) has become a widely researched topic in recent years. SR methods can improve overall image and video quality and create new possibilities for further content analysis.  ...  To analyze the detail-restoration capabilities of image and video SR models, we developed a benchmark based on our own video dataset, which contains complex patterns that SR models generally fail to correctly  ...  NTIRE 2021 Challenge on Video Super-resolution [28] presents evaluation results of quality restoration competition on full (track 1) and half (track 2) framerate, 247 and 223 participants have registered  ... 
arXiv:2203.08923v1 fatcat:x2djqmxgubejtjxjarrjvosrla

NTIRE 2021 Multi-modal Aerial View Object Classification Challenge [article]

Jerrick Liu, Nathan Inkawhich, Oliver Nina, Radu Timofte, Sahil Jain, Bob Lee, Yuru Duan, Wei Wei, Lei Zhang, Songzheng Xu, Yuxuan Sun, Jiaqi Tang (+22 others)
2022 arXiv   pre-print
We discuss the top methods submitted for this competition and evaluate their results on our blind test set.  ...  In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR.  ...  aerial view imagery classification [18] , learning the super-resolution space [20] , quality enhancement of heavily compressed videos [35] , video super-resolution [28] , perceptual image quality  ... 
arXiv:2107.01189v3 fatcat:td5roq6nh5bkdh4m4suc2a4ruq

Flexible Style Image Super-Resolution using Conditional Objective [article]

Seung Ho Park, Young Su Moon, Nam Ik Cho
2022 arXiv   pre-print
Recent studies have significantly enhanced the performance of single-image super-resolution (SR) using convolutional neural networks (CNNs).  ...  Instead of using multiple models, we present a more efficient method to train a single adjustable SR model on various combinations of losses by taking advantage of multi-task learning.  ...  on the Super-Resolution Space Challenge learning track in the NTIRE Challenge 2021 [64, 65] .  ... 
arXiv:2201.04898v3 fatcat:n7fyjvfsxbcvxp6gvhpdcb5w7e

Using Super-Resolution Algorithms for Small Satellite Imagery: A Systematic Review

Kinga Karwowska, Damian Wierzbicki
2022 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Damian Wierzbicki received the Ph.D. degree in photogrammetry and remote sensing from the Mil-  ...  Kinga Karwowska received the M.Sc. degree in geoinformatics in 2020 from the Military University of Technology, Warsaw, Poland, where she is currently working toward the Ph.D. degree with the Doctoral  ...  One of them is the NTIRE Challenge organized as part of the Conference on Computer Vision and Pattern Recognition.  ... 
doi:10.1109/jstars.2022.3167646 fatcat:ghiywhrlx5bjninkzy3dxbmvoy

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution [article]

Long Sun, Jinshan Pan, Jinhui Tang
2022 arXiv   pre-print
In NTIRE 2022, our primary method won the model complexity track of the Efficient Super-Resolution Challenge [23]. The code is available at https://github.com/sunny2109/MobileSR-NTIRE2022.  ...  Lightweight and efficiency are critical drivers for the practical application of image super-resolution (SR) algorithms.  ...  All these results demonstrate the effectiveness of our method. Figure 3 presents visual comparisons on Set14 and Urban100 datasets for a ×4 scale.  ... 
arXiv:2205.15175v1 fatcat:2oyhlmdw4zdjxjn2knbgokea6q

Artificial intelligence in the creative industries: a review

Nantheera Anantrasirichai, David Bull
2021 Artificial Intelligence Review  
(iv) information extraction and enhancement, and (v) data compression.  ...  The potential of AI (or its developers) to win awards for its original creations in competition with human creatives is also limited, based on contemporary technologies.  ...  Upscaling imagery: super-resolution methods Super-resolution (SR) approaches have gained popularity in recent years, enabling the upsampling of images and video spatially or temporally.  ... 
doi:10.1007/s10462-021-10039-7 fatcat:tcctdi7vprfx7mlujvqmpiy3ru

Artificial Intelligence in the Creative Industries: A Review [article]

Nantheera Anantrasirichai, David Bull
2021 arXiv   pre-print
information extraction and enhancement, and v) data compression.  ...  The potential of AI (or its developers) to win awards for its original creations in competition with human creatives is also limited, based on contemporary technologies.  ...  Upscaling Imagery: Super-resolution Methods Super-resolution (SR) approaches have gained popularity in recent years, enabling the upsampling of images and video spatially or temporally.  ... 
arXiv:2007.12391v5 fatcat:mn2xqeylyrbabbu5zwln3admtm

HPRN: Holistic Prior-embedded Relation Network for Spectral Super-Resolution [article]

Chaoxiong Wu, Jiaojiao Li, Rui Song, Yunsong Li, Qian Du
2022 arXiv   pre-print
Spectral super-resolution (SSR) refers to the hyperspectral image (HSI) recovery from an RGB counterpart.  ...  Due to the one-to-many nature of the SSR problem, a single RGB image can be reprojected to many HSIs.  ...  [31] reimplemented and pushed the performance of the work [30] , then introduced a novel shallow network based on the super-resolution method [45] .  ... 
arXiv:2112.14608v2 fatcat:mijiiu6tprelremxnsbllmeq3u
« Previous Showing results 1 — 15 out of 20 results