42 Hits in 5.2 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

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

Blueprint Separable Residual Network for Efficient Image Super-Resolution [article]

Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Jinjin Gu, Yu Qiao, Chao Dong
2022 arXiv   pre-print
Moreover, a smaller variant of our model BSRN-S won the first place in model complexity track of NTIRE 2022 Efficient SR Challenge. The code is available at  ...  The experimental results show that BSRN achieves state-of-the-art performance among existing efficient SR methods.  ...  is partially supported by the National Natural Science Foundation of China (61906184), the Joint Lab of CAS-HK, the Shenzhen Research Program(RCJC20200714114557087), the Shanghai Committee of Science and  ... 
arXiv:2205.05996v1 fatcat:b4u63amzrnbutmz32oyt7bvz5a

NAFSSR: Stereo Image Super-Resolution Using NAFNet [article]

Xiaojie Chu, Liangyu Chen, Wenqing Yu
2022 arXiv   pre-print
With NAFSSR, we won 1st place in the NTIRE 2022 Stereo Image Super-resolution Challenge. Codes and models will be released at  ...  Stereo image super-resolution aims at enhancing the quality of super-resolution results by utilizing the complementary information provided by binocular systems.  ...  NTIRE Stereo Image SR Challenge We submitted a result obtained by the presented approach to the NTIRE 2022 Stereo Image Super-Resolution Challenge [31] .  ... 
arXiv:2204.08714v2 fatcat:gvuvupcdpnh43g2ho44gfo2hhi

Residual Local Feature Network for Efficient Super-Resolution [article]

Fangyuan Kong, Mingxi Li, Songwei Liu, Ding Liu, Jingwen He, Yang Bai, Fangmin Chen, Lean Fu
2022 arXiv   pre-print
In addition, we won the first place in the runtime track of the NTIRE 2022 efficient super-resolution challenge. Code will be available at  ...  However, recent advances in efficient super-resolution focus on reducing the number of parameters and FLOPs, and they aggregate more powerful features by improving feature utilization through complex layer  ...  RLFN for NTIRE 2022 challenge Our team won the 1st place in the main track (Runtime Track) and the 2nd place in the sub-track2 (Overall Performance Track) of NTIRE 2022 efficient super-resolution challenge  ... 
arXiv:2205.07514v1 fatcat:hpcbaukervcoxkjrhpnxvmvxqm

Generative Adversarial Networks for Image Super-Resolution: A Survey [article]

Chunwei Tian, Xuanyu Zhang, Jerry Chun-Wen Lin, Wangmeng Zuo, Yanning Zhang
2022 arXiv   pre-print
Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised  ...  Single image super-resolution (SISR) has played an important role in the field of image processing.  ...  machine learning methods on image super-resolution [21] .  ... 
arXiv:2204.13620v1 fatcat:hlwdqith65cxrbqrnbphjz6u4u

Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution [article]

Zongcai Du, Ding Liu, Jie Liu, Jie Tang, Gangshan Wu, Lean Fu
2022 arXiv   pre-print
Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution. Code is available at  ...  the state-of-the-art EISR model: E-RFDN, the champion in AIM 2020 efficient super-resolution challenge.  ...  HFAB and ERB, which achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution.  ... 
arXiv:2204.08397v1 fatcat:bevbmjebi5czhcenqjkj22furm

Edge-enhanced Feature Distillation Network for Efficient Super-Resolution [article]

Yan Wang
2022 arXiv   pre-print
With the recently massive development in convolution neural networks, numerous lightweight CNN-based image super-resolution methods have been proposed for practical deployments on edge devices.  ...  To address the issue, we conclude block devising, architecture searching, and loss design to obtain a more efficient SR structure.  ...  Challenge results We have participated in NTIRE 2022 Efficient Super-Resolution Challenge [22] .  ... 
arXiv:2204.08759v1 fatcat:ou42slz3mnb75di3hjyia4qso4

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

Seung Ho Park, Young Su Moon, Nam Ik Cho
2022 arXiv   pre-print
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.  ...  Recent studies have significantly enhanced the performance of single-image super-resolution (SR) using convolutional neural networks (CNNs).  ...  on the Super-Resolution Space Challenge learning track in the NTIRE Challenge 2021 [64, 65] .  ... 
arXiv:2201.04898v3 fatcat:n7fyjvfsxbcvxp6gvhpdcb5w7e

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  ...  Lightweight and efficiency are critical drivers for the practical application of image super-resolution (SR) algorithms.  ...  Broader Impact This paper is an exploratory work on lightweight and efficient image super-resolution using a largekernel ConvNet.  ... 
arXiv:2205.15175v1 fatcat:2oyhlmdw4zdjxjn2knbgokea6q

Self-Calibrated Efficient Transformer for Lightweight Super-Resolution [article]

Wenbin Zou, Tian Ye, Weixin Zheng, Yunchen Zhang, Liang Chen, Yi Wu
2022 arXiv   pre-print
We provide comprehensive results on different settings of the overall network. Our proposed method achieves more remarkable performance than baseline methods.  ...  Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance.  ...  The SCET method is a competing entry in NTIRE 2022 Efficient Super-Resolution challenge [25] .  ... 
arXiv:2204.08913v1 fatcat:qbgrdvikefhh5halvu3x4ls4zm

BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment [article]

Ziwei Luo, Youwei Li, Shen Cheng, Lei Yu, Qi Wu, Zhihong Wen, Haoqiang Fan, Jian Sun, Shuaicheng Liu
2022 arXiv   pre-print
Further, our BSRT wins the championship in the NTIRE2022 Burst Super-Resolution Challenge.  ...  To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction.  ...  Furthermore, our proposed BSRT wins 1st place in real-world track of the NTIRE 2022 Burst Super-Resolution Challenge. Figure 2 . 2 Figure2.  ... 
arXiv:2204.08332v2 fatcat:zwmo7ssvnngqpdw7k4gpw2ssba

Reflash Dropout in Image Super-Resolution [article]

Xiangtao Kong, Xina Liu, Jinjin Gu, Yu Qiao, Chao Dong
2022 arXiv   pre-print
Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR).  ...  The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks.  ...  is partially supported by the National Natural Science Foundation of China (61906184), the Joint Lab of CAS-HK, the Shenzhen Research Program (RCJC20200714114557087), the Shanghai Committee of Science and  ... 
arXiv:2112.12089v3 fatcat:ruhoruxfbferdcgfbskckkdy2e

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

Efficient Image Super-Resolution via Self-Calibrated Feature Fuse

Congming Tan, Shuli Cheng, Liejun Wang
2022 Sensors  
Recently, many super-resolution reconstruction (SR) feedforward networks based on deep learning have been proposed. These networks enable the reconstructed images to achieve convincing results.  ...  In this paper, we propose the efficient image super-resolution network via Self-Calibrated Feature Fuse, named SCFFN, by constructing the self-calibrated feature fuse block (SCFFB).  ...  Discussion Through the above ablation research and comparative experiments, we found that the image super-resolution reconstruction has great challenges in terms of trade-offs among network parameters,  ... 
doi:10.3390/s22010329 pmid:35009871 pmcid:PMC8749868 fatcat:2xn2ys6q5bfrvn46jf3k6t4k5i
« Previous Showing results 1 — 15 out of 42 results