Sitesinformation.com

Keyword Analysis & Research: cufed5


Keyword Analysis

Keyword CPC PCC Volume Score Length of keyword
cufed50.50.83558806

Keyword Research: People who searched cufed5 also searched

Keyword CPC PCC Volume Score
cufed50.830.2874647
cufed5 dataset0.960.2514963

Search Results related to cufed5 on Search Engine

  • SRNTT - GitHub Pages

    github.io

    https://zzutk.github.io/SRNTT-Project-Page/

    WEBTesting Dataset (CUFED5, 233MB) Training Dataset (CUFED, 1.1GB) Training Dataset (DIV2K, 3.7GB) Results. Quantitative Evaluation. Qualitative Evaluation. Percentage of votes of SRNTT as compared to each of other methods in the user study. Texture Transfer with Different References (bottom-right)

    DA: 94 PA: 81 MOZ Rank: 42 Up or Down: Up

  • CUFED5 - 4x upscaling Benchmark (Image Super-Resolution)

    paperswithcode.com

    https://paperswithcode.com/sota/image-super-resolution-on-cufed5-4x-upscaling

    WEBImage Super-Resolution by Neural Texture Transfer. The current state-of-the-art on CUFED5 - 4x upscaling is Extracter-rec. See a full comparison of 2 papers with code.

    DA: 95 PA: 22 MOZ Rank: 46 Up or Down: Up

  • Image Super-Resolution by Neural Texture Transfer - arXiv.org

    arxiv.org

    https://arxiv.org/pdf/1903.00834

    WEBnew dataset, named CUFED5, which provides training and testing sets accompanied with references of different simi-larity levels in terms of content, texture, color, illumination, view point, etc. The main contributions of this paper are: We explore a more general RefSR problem, breaking the performance barrier in SISR (i.e., lack of texture

    DA: 93 PA: 61 MOZ Rank: 81 Up or Down: Up

  • Image Super-Resolution by Neural Texture Transfer - CVF …

    thecvf.com

    https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Image_Super-Resolution_by_Neural_Texture_Transfer_CVPR_2019_paper.pdf

    WEBnew dataset, named CUFED5, which provides training and testing sets accompanied with references of different simi-larity levels in terms of content, texture, color, illumination, view point, etc. The main contributions of this paper are: • We explore a more general RefSR problem, breaking the performance barrier in SISR (i.e., lack of texture

    DA: 98 PA: 84 MOZ Rank: 83 Up or Down: Up

  • Reference-Based Image Super-Resolution with Deformable

    springer.com

    https://link.springer.com/chapter/10.1007/978-3-031-19797-0_19

    WEBNov 3, 2022 · For fair comparisons, the above models are trained on CUFED5 training set, and tested on CUFED5 testing set, Urban100, Manga109, Sun80 and WR-SR. In this experiment, we train our model on two cases only with reconstruction loss (denoted as ‘ …

    DA: 55 PA: 58 MOZ Rank: 25 Up or Down: Up

  • ZZUTK/SRNTT: Image Super-Resolution by Neural Texture Transfer - GitHub

    github.com

    https://github.com/ZZUTK/SRNTT

    WEBTesting set. This repo includes one grounp of samples from the CUFED5 dataset, where each input image corresponds to five reference images (different from the paper) with different degrees of similarity to the input image. Please download the full dataset by. $ python download_dataset.py --dataset_name CUFED5.

    DA: 93 PA: 31 MOZ Rank: 89 Up or Down: Up

  • Image Super-Resolution by Neural Texture Transfer

    paperswithcode.com

    https://paperswithcode.com/paper/image-super-resolution-by-neural-texture

    WEBRanked #2 on Image Super-Resolution on CUFED5 - 4x upscaling. Get a GitHub badge. Methods. Edit. #2 best model for Image Super-Resolution on CUFED5 - 4x upscaling (PSNR metric)

    DA: 81 PA: 35 MOZ Rank: 72 Up or Down: Up

  • Towards Content-Independent Multi-Reference Super-Resolution …

    springer.com

    https://link.springer.com/chapter/10.1007/978-3-030-58595-2_4

    WEBNov 20, 2020 · We further compare qualitative evaluation with similar references. We selected three samples from CUFED5 and compared SRCNN , SRGAN , SRNTT , and our baseline MDSR in the lower part of Fig. 5. We achieve better results in texture details and a huge improvement over baseline.

    DA: 18 PA: 5 MOZ Rank: 71 Up or Down: Up

  • Online Learning for Reference-Based Super-Resolution - MDPI

    mdpi.com

    https://www.mdpi.com/2079-9292/11/7/1064

    WEBMar 28, 2022 · Online learning is a method for exploiting input data to update deep networks in the test stage to derive potential performance improvement. Existing online learning methods for single-image super-resolution (SISR) utilize an input low-resolution (LR) image for the online adaptation of deep networks.

    DA: 26 PA: 89 MOZ Rank: 79 Up or Down: Up

  • Reference-Conditioned Super-Resolution by Neural Texture …

    researchgate.net

    https://www.researchgate.net/publication/324435870_Reference-Conditioned_Super-Resolution_by_Neural_Texture_Transfer

    WEBApr 10, 2018 · we propose a new dataset, named CUFED5, which provides training and testing sets accompanied with references of five similarity lev els that vary in content, texture, color, illumination, and ...

    DA: 74 PA: 11 MOZ Rank: 33 Up or Down: Up