Decoder-Side Quality Enhancement of JPEG Images Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients. Busson, A. J. G., Mendes, P. R. C., de S. Moraes, D., da Veiga, Á. M. G., Colcher, S., & Guedes, Á. L. V. In Proceedings of the Brazilian Symposium on Multimedia and the Web, of WebMedia '20, pages 129–136, 2020. Association for Computing Machinery. ![Decoder-Side Quality Enhancement of JPEG Images Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper Year doi abstract bibtex 11 downloads Many recent works have successfully applied some types of Convolutional Neural Networks (CNNs) to reduce the noticeable distortion resulting from the lossy JPEG compression technique. Most of them are built upon the processing made on the spatial domain. In this work, we propose a JPEG image decoder that is purely based on the frequency-to-frequency domain: it reads the quantized DCT coefficients received from a low-quality image bitstream and, using a deep learning-based model, predicts the missing coefficients in order to recompose the same image with enhanced quality. In experiments with two datasets, our best model was able to improve from images with quantized DCT coefficients corresponding to a Qualityz Factor (QF) of 10 to enhanced quality images with QF slightly higher than 20.
@inproceedings{busson_decoder-side_2020,
location = {New York, {NY}, {USA}},
title = {Decoder-Side Quality Enhancement of {JPEG} Images Using Deep Learning-Based Prediction Models for Quantized {DCT} Coefficients},
isbn = {978-1-4503-8196-3},
url = {https://doi.org/10.1145/3428658.3430966},
doi = {10.1145/3428658.3430966},
series = {{WebMedia} '20},
abstract = {Many recent works have successfully applied some types of Convolutional Neural Networks ({CNNs}) to reduce the noticeable distortion resulting from the lossy {JPEG} compression technique. Most of them are built upon the processing made on the spatial domain. In this work, we propose a {JPEG} image decoder that is purely based on the frequency-to-frequency domain: it reads the quantized {DCT} coefficients received from a low-quality image bitstream and, using a deep learning-based model, predicts the missing coefficients in order to recompose the same image with enhanced quality. In experiments with two datasets, our best model was able to improve from images with quantized {DCT} coefficients corresponding to a Qualityz Factor ({QF}) of 10 to enhanced quality images with {QF} slightly higher than 20.},
pages = {129--136},
booktitle = {Proceedings of the Brazilian Symposium on Multimedia and the Web},
publisher = {Association for Computing Machinery},
author = {Busson, Antonio José G. and Mendes, Paulo Renato C. and de S. Moraes, Daniel and da Veiga, Álvaro Mário G. and Colcher, Sérgio and Guedes, Álan Lívio V.},
urlyear = {2020},
year = {2020},
keywords = {Convolutional Neural Networks, {DCT}, Deep learning, Image compression, {JPEG}},
}
Downloads: 11
{"_id":"cJmTa9xXbADGunDas","bibbaseid":"busson-mendes-desmoraes-daveiga-colcher-guedes-decodersidequalityenhancementofjpegimagesusingdeeplearningbasedpredictionmodelsforquantizeddctcoefficients-2020","authorIDs":[],"author_short":["Busson, A. J. G.","Mendes, P. R. C.","de S. Moraes, D.","da Veiga, Á. M. G.","Colcher, S.","Guedes, Á. L. V."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","location":"New York, NY, USA","title":"Decoder-Side Quality Enhancement of JPEG Images Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients","isbn":"978-1-4503-8196-3","url":"https://doi.org/10.1145/3428658.3430966","doi":"10.1145/3428658.3430966","series":"WebMedia '20","abstract":"Many recent works have successfully applied some types of Convolutional Neural Networks (CNNs) to reduce the noticeable distortion resulting from the lossy JPEG compression technique. Most of them are built upon the processing made on the spatial domain. In this work, we propose a JPEG image decoder that is purely based on the frequency-to-frequency domain: it reads the quantized DCT coefficients received from a low-quality image bitstream and, using a deep learning-based model, predicts the missing coefficients in order to recompose the same image with enhanced quality. In experiments with two datasets, our best model was able to improve from images with quantized DCT coefficients corresponding to a Qualityz Factor (QF) of 10 to enhanced quality images with QF slightly higher than 20.","pages":"129–136","booktitle":"Proceedings of the Brazilian Symposium on Multimedia and the Web","publisher":"Association for Computing Machinery","author":[{"propositions":[],"lastnames":["Busson"],"firstnames":["Antonio","José","G."],"suffixes":[]},{"propositions":[],"lastnames":["Mendes"],"firstnames":["Paulo","Renato","C."],"suffixes":[]},{"propositions":["de"],"lastnames":["S.","Moraes"],"firstnames":["Daniel"],"suffixes":[]},{"propositions":["da"],"lastnames":["Veiga"],"firstnames":["Álvaro","Mário","G."],"suffixes":[]},{"propositions":[],"lastnames":["Colcher"],"firstnames":["Sérgio"],"suffixes":[]},{"propositions":[],"lastnames":["Guedes"],"firstnames":["Álan","Lívio","V."],"suffixes":[]}],"urlyear":"2020","year":"2020","keywords":"Convolutional Neural Networks, DCT, Deep learning, Image compression, JPEG","bibtex":"@inproceedings{busson_decoder-side_2020,\n\tlocation = {New York, {NY}, {USA}},\n\ttitle = {Decoder-Side Quality Enhancement of {JPEG} Images Using Deep Learning-Based Prediction Models for Quantized {DCT} Coefficients},\n\tisbn = {978-1-4503-8196-3},\n\turl = {https://doi.org/10.1145/3428658.3430966},\n\tdoi = {10.1145/3428658.3430966},\n\tseries = {{WebMedia} '20},\n\tabstract = {Many recent works have successfully applied some types of Convolutional Neural Networks ({CNNs}) to reduce the noticeable distortion resulting from the lossy {JPEG} compression technique. Most of them are built upon the processing made on the spatial domain. In this work, we propose a {JPEG} image decoder that is purely based on the frequency-to-frequency domain: it reads the quantized {DCT} coefficients received from a low-quality image bitstream and, using a deep learning-based model, predicts the missing coefficients in order to recompose the same image with enhanced quality. In experiments with two datasets, our best model was able to improve from images with quantized {DCT} coefficients corresponding to a Qualityz Factor ({QF}) of 10 to enhanced quality images with {QF} slightly higher than 20.},\n\tpages = {129--136},\n\tbooktitle = {Proceedings of the Brazilian Symposium on Multimedia and the Web},\n\tpublisher = {Association for Computing Machinery},\n\tauthor = {Busson, Antonio José G. and Mendes, Paulo Renato C. and de S. Moraes, Daniel and da Veiga, Álvaro Mário G. and Colcher, Sérgio and Guedes, Álan Lívio V.},\n\turlyear = {2020},\n\tyear = {2020},\n\tkeywords = {Convolutional Neural Networks, {DCT}, Deep learning, Image compression, {JPEG}},\n}\n\n","author_short":["Busson, A. J. G.","Mendes, P. R. C.","de S. Moraes, D.","da Veiga, Á. M. G.","Colcher, S.","Guedes, Á. L. V."],"key":"busson_decoder-side_2020","id":"busson_decoder-side_2020","bibbaseid":"busson-mendes-desmoraes-daveiga-colcher-guedes-decodersidequalityenhancementofjpegimagesusingdeeplearningbasedpredictionmodelsforquantizeddctcoefficients-2020","role":"author","urls":{"Paper":"https://doi.org/10.1145/3428658.3430966","Year":"http://www.telemidia.puc-rio.br/files/biblio/2020"},"keyword":["Convolutional Neural Networks","DCT","Deep learning","Image compression","JPEG"],"metadata":{"authorlinks":{}},"downloads":11},"bibtype":"inproceedings","biburl":"http://www.telemidia.puc-rio.br/files/biblio/all.bib","creationDate":"2021-01-15T19:20:27.456Z","downloads":11,"keywords":["convolutional neural networks","dct","deep learning","image compression","jpeg"],"search_terms":["decoder","side","quality","enhancement","jpeg","images","using","deep","learning","based","prediction","models","quantized","dct","coefficients","busson","mendes","de s. moraes","da veiga","colcher","guedes"],"title":"Decoder-Side Quality Enhancement of JPEG Images Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients","year":2020,"dataSources":["gXSBTZhj3xCWydoZF"]}