{"type":"ScholarlyArticle","title":"JPEG Artifacts Removal via Compression Quality Ranker-Guided Networks","authors":[{"name":"Menglu Wang","slug":"menglu-wang","given":"Menglu","family":"Wang","affiliation":"University of Science and Technology of China , China"},{"name":"Xueyang Fu","slug":"xueyang-fu","given":"Xueyang","family":"Fu","affiliation":"University of Science and Technology of China , China"},{"name":"Zepei Sun","slug":"zepei-sun","given":"Zepei","family":"Sun","affiliation":"Xidian University , China"},{"name":"Zheng-Jun Zha","slug":"zheng-jun-zha","given":"Zheng-Jun","family":"Zha","affiliation":"University of Science and Technology of China , China"}],"abstract":"Existing deep learning-based image de-blocking methods use only pixel-level loss functions to guide network training. The JPEG compression factor, which reflects the degradation degree, has not been fully utilized. However, due to the non-differentiability, the compression factor cannot be directly utilized to train deep networks. To solve this problem, we propose compression quality ranker-guided networks for this specific JPEG artifacts removal. We first design a quality ranker to measure the compression degree, which is highly correlated with the JPEG quality. Based on this differentiable ranker, we then propose one quality-related loss and one feature matching loss to guide de-blocking and perceptual quality optimization. In addition, we utilize dilated convolutions to extract multi-scale features, which enables our single model to handle multiple compression quality factors. Our method can implicitly use the information contained in the compression factors to produce better results. Experiments demonstrate that our model can achieve comparable or even better performance in both quantitative and qualitative measurements.","doi":"10.24963/ijcai.2020/79","url":"https://ijcai.org/proceedings/2020/79","pdf":"https://ijcai.org/proceedings/2020/0079.pdf","markdown":"https://ijcai.org/proceedings/2020/79.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/79","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Computer Vision","track":"Main track","number":79,"pages":{"first":566,"last":572},"keywords":["Computer Vision: Computational Photography, Photometry, Shape from X","Machine Learning: Deep Learning: Convolutional networks","Computer Vision: Perception"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25416/file_25416.m3u8","length_sec":273,"provider":"hls"}],"references":[{"position":1,"raw":"[Agustsson and Timofte, 2017] E. Agustsson and R. Timo- fte. Ntire 2017 challenge on single image super-resolution: Dataset and study. In CVPR Workshops, 2017.","title":"Ntire 2017 challenge on single image super-resolution: Dataset and study","authors":"E Agustsson, R Timofte","year":"2017","venue":"CVPR Workshops","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Arbelaez et al., 2010] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5):898-916, 2010.","title":"Contour detection and hierarchical image segmentation","authors":"P Arbelaez, M Maire, C Fowlkes, J Malik","year":"2010","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chang et al., 2013] H. Chang, M. K Ng, and T. Zeng. Re- ducing artifacts in jpeg decompression via a learned dictio- nary. IEEE Transactions on Signal Processing, 62(3):718- 728, 2013.","title":"Reducing artifacts in jpeg decompression via a learned dictionary","authors":"H Chang, M K Ng, T Zeng","year":"2013","venue":"IEEE Transactions on Signal Processing","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen and Pock, 2017] Y. Chen and T. Pock. A flexible framework for fast and effective image restoration. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 39(6):1256-1272, 2017.","title":"A flexible framework for fast and effective image restoration","authors":"Y Chen, T Pock","year":"2017","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dong et al., 2015] C. Dong, Y. Deng, C. Change Loy, and X. Tang. Compression artifacts reduction by a deep con- volutional network. In ICCV, pages 576-584, 2015.","title":"Compression artifacts reduction by a deep convolutional network","authors":"C Dong, Y Deng, C Change Loy, X Tang","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fan et al., 2018] Q. Fan, D. Chen, L. Yuan, G. Hua, N. Yu, and B. Chen. Decouple learning for parameterized image operators. In ECCV, pages 442-458, 2018.","title":"Decouple learning for parameterized image operators","authors":"Q Fan, D Chen, L Yuan, G Hua, N Yu, B Chen","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Foi et al., 2007] A. Foi, V. Katkovnik, and K. Egiazar- ian. Pointwise shape-adaptive dct for high-quality de- noising and deblocking of grayscale and color images. IEEE Transactions on Image Processing, 16(5):1395- 1411, 2007.","title":"Pointwise shape-adaptive dct for high-quality denoising and deblocking of grayscale and color images","authors":"A Foi, V Katkovnik, K Egiazarian","year":"2007","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fu et al., 2019] X. Fu, Z.-J. Zha, F. Wu, X. Ding, and J. Paisley. Jpeg artifacts reduction via deep convolutional sparse coding. In ICCV, pages 2501-2510, 2019.","title":"Jpeg artifacts reduction via deep convolutional sparse coding","authors":"X Fu, Z.-J Zha, F Wu, X Ding, J Paisley","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Goodfellow et al., 2014] I.","title":null,"authors":"Goodfellow","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In NeurIPS, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"J Goodfellow, M Pouget-Abadie, B Mirza, D Xu, S Warde-Farley, A Ozair, Y Courville, Bengio","year":"2014","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Guo and Chao, 2017] J. Guo and H. Chao. One-to-many network for visually pleasing compression artifacts reduc- tion. In CVPR, pages 3038-3047, 2017.","title":"One-to-many network for visually pleasing compression artifacts reduction","authors":"Guo, ] J Chao, H Guo, Chao","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2016] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, 2016.","title":"Deep residual learning for image recognition","authors":"K He, X Zhang, S Ren, J Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jancsary et al., 2012] J. Jancsary, S. Nowozin, and C. Rother. Loss-specific training of non-parametric image restoration models: A new state of the art. In ECCV, pages 112-125, 2012.","title":"Loss-specific training of non-parametric image restoration models: A new state of the art","authors":"J Jancsary, S Nowozin, C Rother","year":"2012","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Johnson et al., 2016] J. Johnson, A. Alahi, and F.-F. Li. Perceptual losses for real-time style transfer and super- resolution. In ECCV, pages 694-711, 2016.","title":"Perceptual losses for real-time style transfer and superresolution","authors":"J Johnson, A Alahi, F.-F Li","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2014] Y. Li, F. Guo, R. T Tan, and M. S Brown. A contrast enhancement framework with jpeg artifacts sup- pression. In ECCV, pages 174-188, 2014.","title":"A contrast enhancement framework with jpeg artifacts suppression","authors":"Y Li, F Guo, R T Tan, M S Brown","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2017] T. Li, X. He, L. Qing, Q. Teng, and H. Chen. An iterative framework of cascaded deblocking and super- resolution for compressed images. IEEE Transactions on Multimedia, 20(6):1305-1320, 2017.","title":"An iterative framework of cascaded deblocking and superresolution for compressed images","authors":"T Li, X He, L Qing, Q Teng, H Chen","year":"2017","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2018] D. Liu, B. Wen, X. Liu, Z. Wang, and T. S Huang. When image denoising meets high-level vision tasks: a deep learning approach. In IJCAI, 2018.","title":"When image denoising meets high-level vision tasks: a deep learning approach","authors":"D Liu, B Wen, X Liu, Z Wang, T S Huang","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/117"},{"position":19,"raw":"[Liu et al., 2019] D. Liu, H. Zhang, and Z. Xiong. On the classification-distortion-perception tradeoff. In NeurIPS, pages 1204-1213, 2019.","title":"On the classification-distortion-perception tradeoff","authors":"D Liu, H Zhang, Z Xiong","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Saquil et al., 2018] Y. Saquil, K. I. Kim, and P. Hall. Rank- ing cgans: Subjective control over semantic image at- tributes. arXiv preprint arXiv:1804.04082, 2018.","title":"Ranking cgans: Subjective control over semantic image attributes","authors":"Y Saquil, K I Kim, P Hall","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sheikh, 2005] HR Sheikh. Live image quality assess- ment database release 2. http://live. ece. utexas. edu/research/quality, 2005.","title":"HR Sheikh. Live image quality assessment database release 2","authors":"Sheikh","year":"2005","venue":null,"doi":null,"url":"http://live.ece.utexas.edu/research/quality,2005","internal_url":null},{"position":22,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vandal et al., 2018] T. Vandal, E. Kodra, S. Ganguly, A. R Michaelis, R. R Nemani, and A. R Ganguly. Generating high resolution climate change projections through single image super-resolution: An abridged version. In IJCAI, 2018.","title":"Generating high resolution climate change projections through single image super-resolution: An abridged version","authors":"T Vandal, E Kodra, S Ganguly, A Michaelis, R R Nemani, A R Ganguly","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/759"},{"position":24,"raw":"[Wang et al., 2016] Z. Wang, D. Liu, S. Chang, Q. Ling, Y. Yang, and T. S Huang. D 3 : Deep dual-domain based fast restoration of jpeg-compressed images. In CVPR, 2016.","title":"D 3 : Deep dual-domain based fast restoration of jpeg-compressed images","authors":"Z Wang, D Liu, S Chang, Q Ling, Y Yang, T S Huang","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2019] N. Wang, J. Li, L. Zhang, and B. Du. Musical: multi-scale image contextual attention learning for inpainting. In IJCAI, pages 3748-3754, 2019.","title":"Musical: multi-scale image contextual attention learning for inpainting","authors":"N Wang, J Li, L Zhang, B Du","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/520"},{"position":26,"raw":"[Yim and Bovik, 2010] C. Yim and A. C. Bovik. Quality as- sessment of deblocked images. IEEE Transactions on Im- age Processing, 20(1):88-98, 2010.","title":"Quality assessment of deblocked images","authors":"C Yim, A C Bovik","year":"2010","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zeyde et al., 2010] R. Zeyde, M. Elad, and M. Protter. On single image scale-up using sparse-representations. In In- ternational conference on curves and surfaces, 2010.","title":"On single image scale-up using sparse-representations","authors":"R Zeyde, M Elad, M Protter","year":"2010","venue":"International conference on curves and surfaces","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2017] K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans- actions on Image Processing, 26(7):3142-3155, 2017.","title":"Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising","authors":"K Zhang, W Zuo, Y Chen, D Meng, L Zhang","year":"2017","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2018] R. Zhang, S. Tang, L. Liu, Y. Zhang, J. Li, and S. Yan. High resolution feature recovering for accelerating urban scene parsing. In IJCAI, 2018.","title":"High resolution feature recovering for accelerating urban scene parsing","authors":"R Zhang, S Tang, L Liu, Y Zhang, J Li, S Yan","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/161"},{"position":30,"raw":"[Zhang et al., 2019a] W. Zhang, Y. Liu, C. Dong, and Y. Qiao. RanksrGan: Generative adversarial networks with ranker for image super-resolution. In ICCV, 2019.","title":"RanksrGan: Generative adversarial networks with ranker for image super-resolution","authors":"Zhang","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang et al., 2019b] Y. Zhang, K. Li, K. Li, B. Zhong, and Y. Fu. Residual non-local attention networks for image restoration. In ICLR, 2019.","title":"Residual non-local attention networks for image restoration","authors":"Zhang","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu et al., 2018] H. Zhu, X. Peng, V. Chandrasekhar, L. Li, and J.-H. Lim. Dehazegan: When image dehazing meets differential programming. In IJCAI, pages 1234-1240, 2018.","title":"Dehazegan: When image dehazing meets differential programming","authors":"H Zhu, X Peng, V Chandrasekhar, L Li, J.-H Lim","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/172"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}