ABSTRACT
Social media filters cause various manipulations in the original image. While these manipulations make the images visibly pleasant, they can affect their authenticity and the performance of further image-processing tasks. Therefore, removing these social media filters is a crucial pre-processing step for the data pipeline of any image-processing task. In this paper, a recurrent residual UNet-based model is proposed to remove the filters. The recurrent residual block allows the units of each layer to evolve over discrete time steps so that the activity of each unit is modulated by the activities of its neighboring units. Because of this characteristic, the networks learn contextual information more efficiently and effectively. Assuming that a filter can be noise, the proposed model learns the feature representation of the filter, and then the original, unfiltered image is retrieved by taking the residuals of the input image and the filter representation. The experimental results show that the proposed model outperforms both supervised and unsupervised methods by a considerable margin in the IFFI dataset.
- Abdelrahman Abdelhamed, Mahmoud Afifi, Radu Timofte, and Michael S Brown. 2020. NTIRE 2020 challenge on real image denoising: Dataset, methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 496–497.Google Scholar
- Abdelrahman Abdelhamed, Stephen Lin, and Michael S Brown. 2018. A high-quality denoising dataset for smartphone cameras. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1692–1700.Google ScholarCross Ref
- Abdelrahman Abdelhamed, Radu Timofte, and Michael S Brown. 2019. NTIRE 2019 challenge on real image denoising: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 0–0.Google Scholar
- Md Zahangir Alom, Mahmudul Hasan, Chris Yakopcic, Tarek M Taha, and Vijayan K Asari. 2018. Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv preprint arXiv:1802.06955(2018).Google Scholar
- Md Zahangir Alom, Mahmudul Hasan, Chris Yakopcic, Tarek M Taha, and Vijayan K Asari. 2020. Improved inception-residual convolutional neural network for object recognition. Neural Computing and Applications 32, 1 (2020), 279–293.Google ScholarDigital Library
- Luca Bertinetto, Jack Valmadre, Joao F Henriques, Andrea Vedaldi, and Philip HS Torr. 2016. Fully-convolutional siamese networks for object tracking. In European conference on computer vision. Springer, 850–865.Google ScholarCross Ref
- Alex Bewley, Zongyuan Ge, Lionel Ott, Fabio Ramos, and Ben Upcroft. 2016. Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP). IEEE, 3464–3468.Google ScholarCross Ref
- Simone Biancoa, Claudio Cusanob, Flavio Piccolia, and Raimondo Schettinia. [n.d.]. Artistic Photo Filter Removal Using CNNs. ([n. d.]).Google Scholar
- Antoni Buades, Bartomeu Coll, and J-M Morel. 2005. A non-local algorithm for image denoising. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), Vol. 2. Ieee, 60–65.Google Scholar
- Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, and Jian Sun. 2022. Simple baselines for image restoration. arXiv preprint arXiv:2204.04676(2022).Google Scholar
- Yu-Hsiu Chen, Ting-Hsuan Chao, Sheng-Yi Bai, Yen-Liang Lin, Wen-Chin Chen, and Winston H Hsu. 2015. Filter-invariant image classification on social media photos. In Proceedings of the 23rd ACM international conference on Multimedia. 855–858.Google ScholarDigital Library
- Wei-Ta Chu and Yu-Tzu Fan. 2019. Photo filter classification and filter recommendation without much manual labeling. In 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP). IEEE, 1–6.Google ScholarCross Ref
- Kostadin Dabov, Alessandro Foi, Vladimir Katkovnik, and Karen Egiazarian. 2007. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on image processing 16, 8 (2007), 2080–2095.Google ScholarCross Ref
- Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Kun Zhang, and Dacheng Tao. 2019. Geometry-consistent generative adversarial networks for one-sided unsupervised domain mapping. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2427–2436.Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.Google ScholarCross Ref
- Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2017. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1125–1134.Google ScholarCross Ref
- Furkan Kinli, Baris Ozcan, and Furkan Kirac. 2021. Instagram filter removal on fashionable images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 736–745.Google ScholarCross Ref
- Furkan Kınlı, Barış Özcan, and Furkan Kıraç. 2022. Patch-wise Contrastive Style Learning for Instagram Filter Removal. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 578–588.Google ScholarCross Ref
- Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang. 2018. Fast and accurate image super-resolution with deep laplacian pyramid networks. IEEE transactions on pattern analysis and machine intelligence 41, 11(2018), 2599–2613.Google Scholar
- Hsin-Ying Lee, Hung-Yu Tseng, Qi Mao, Jia-Bin Huang, Yu-Ding Lu, Maneesh Singh, and Ming-Hsuan Yang. 2020. Drit++: Diverse image-to-image translation via disentangled representations. International Journal of Computer Vision 128, 10 (2020), 2402–2417.Google ScholarDigital Library
- Ming Liang and Xiaolin Hu. 2015. Recurrent convolutional neural network for object recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3367–3375.Google ScholarCross Ref
- Ming Liang and Xiaolin Hu. 2015. Recurrent convolutional neural network for object recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3367–3375.Google ScholarCross Ref
- Taesung Park, Alexei A Efros, Richard Zhang, and Jun-Yan Zhu. 2020. Contrastive learning for unpaired image-to-image translation. In European conference on computer vision. Springer, 319–345.Google ScholarDigital Library
- Tobias Plotz and Stefan Roth. 2017. Benchmarking denoising algorithms with real photographs. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1586–1595.Google ScholarCross Ref
- Yijun Quan, Xufeng Lin, and Chang-Tsun Li. 2018. Provenance analysis for instagram photos. In Australasian Conference on Data Mining. Springer, 372–383.Google Scholar
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241.Google ScholarCross Ref
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241.Google ScholarCross Ref
- Oleksii Sidorov. 2019. Conditional gans for multi-illuminant color constancy: Revolution or yet another approach?. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 0–0.Google ScholarCross Ref
- Jingwen Su, Boyan Xu, and Hujun Yin. 2022. A survey of deep learning approaches to image restoration. Neurocomputing 487(2022), 46–65.Google ScholarDigital Library
- Chunwei Tian, Lunke Fei, Wenxian Zheng, Yong Xu, Wangmeng Zuo, and Chia-Wen Lin. 2020. Deep learning on image denoising: An overview. Neural Networks 131(2020), 251–275.Google ScholarCross Ref
- Zhe Wu, Zuxuan Wu, Bharat Singh, and Larry Davis. 2020. Recognizing instagram filtered images with feature de-stylization. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 12418–12425.Google ScholarCross Ref
- Syed Waqas Zamir and Aditya etc Arora. 2020. Learning Enriched Features for Real Image Restoration and Enhancement. In Computer Vision – ECCV 2020. Springer International Publishing, Cham, 492–511.Google ScholarDigital Library
- Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2017. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE transactions on image processing 26, 7 (2017), 3142–3155.Google ScholarDigital Library
- Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2017. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE transactions on image processing 26, 7 (2017), 3142–3155.Google ScholarDigital Library
- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision. 2223–2232.Google ScholarCross Ref
- Qiang Zuo, Songyu Chen, and Zhifang Wang. 2021. R2AU-Net: attention recurrent residual convolutional neural network for multimodal medical image segmentation. Security and Communication Networks 2021 (2021).Google Scholar
Index Terms
- Insta Net: Recurrent Residual Network for Instagram Filter Removal✱
Recommendations
Identifying Optimal Gaussian Filter for Gaussian Noise Removal
NCVPRIPG '11: Proceedings of the 2011 Third National Conference on Computer Vision, Pattern Recognition, Image Processing and GraphicsIn this paper we show that the knowledge of noise statistics contaminating a signal can be effectively used to choose an optimal Gaussian filter to eliminate noise. Very specifically, we show that the additive white Gaussian noise (AWGN) contaminating a ...
Modified Double Bilateral Filter for Sharpness Enhancement and Noise Removal
ACE '10: Proceedings of the 2010 International Conference on Advances in Computer EngineeringThis paper propose a double bilateral filter that extends the classical bilateral filtering for image noise removal. A new median-metric weighting function is introduced by incorporating a 3 3 median filter into a second bilateral filter. A variety of ...
Modified switching median filter for impulse noise removal
In this paper, a modified switching median filter is presented for noise reduction in color images that are corrupted with impulse (salt and pepper) noise. It is a two-phase noise detector: in the first phase, we use the adaptive vector median filter ...
Comments