{"type":"ScholarlyArticle","title":"WBFlow: Few-shot White Balance for sRGB Images via Reversible Neural Flows","authors":[{"name":"Chunxiao Li","slug":"chunxiao-li","given":"Chunxiao","family":"Li","affiliation":"School of Computer Science (National Pilot Software Engineering School) , Beijing University of Posts and Telecommunications"},{"name":"Xuejing Kang","slug":"xuejing-kang","given":"Xuejing","family":"Kang","affiliation":"School of Computer Science (National Pilot Software Engineering School) , Beijing University of Posts and Telecommunications"},{"name":"Anlong Ming","slug":"anlong-ming","given":"Anlong","family":"Ming","affiliation":"School of Computer Science (National Pilot Software Engineering School) , Beijing University of Posts and Telecommunications"}],"abstract":"The sRGB white balance methods aim to correct  the nonlinear color cast of sRGB images without  accessing raw values.  Although existing methods  have achieved increasingly better results, their generalization  to sRGB images from multiple cameras  is still under explored.  In this paper, we propose  the network named WBFlow that not only performs  superior white balance for sRGB images but also  generalizes well to multiple cameras.  Specifically,  we take advantage of neural flow to ensure the reversibility  of WBFlow, which enables lossless rendering  of color cast sRGB images back to pseudo  raw features for linear white balancing and thus  achieves superior performance.  Furthermore, inspired  by camera transformation approaches, we  have designed a camera transformation (CT) in  pseudo raw feature space to generalize WBFlow  for different cameras via few shot learning.  By  utilizing a few sRGB images from an untrained  camera, our WBFlow can perform well on this  camera by learning the camera specific parameters  of CT.  Extensive experiments show that WBFlow  achieves superior camera generalization and accuracy  on three public datasets as well as our rendered  multiple camera sRGB dataset.  Our code is available  at https://github.com/ChunxiaoLe/WBFlow.","doi":"10.24963/ijcai.2023/114","url":"https://ijcai.org/proceedings/2023/114","pdf":"https://ijcai.org/proceedings/2023/0114.pdf","markdown":"https://ijcai.org/proceedings/2023/114.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/114","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Computer Vision","track":"Main Track","number":114,"pages":{"first":1026,"last":1034},"keywords":["Computer Vision: CV: Computational photography","Computer Vision: CV: Applications"],"videos":[],"references":[{"position":1,"raw":"[Afifi and Brown, 2019] Mahmoud Afifi and Michael S Brown. What else can fool deep learning? address- ing color constancy errors on deep neural network perfor- mance. In Proceedings of the IEEE International Confer- ence on Computer Vision, pages 243-252, 2019.","title":"What else can fool deep learning? addressing color constancy errors on deep neural network performance","authors":"Mahmoud Afifi, Michael S Brown","year":"2019","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Afifi and Brown, 2020a] Mahmoud Afifi and Michael S Brown. Deep white-balance editing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 1397-1406, 2020.","title":"Deep white-balance editing","authors":"Brown Afifi, Mahmoud Afifi, Michael S Brown","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Afifi and Brown, 2020b] Mahmoud Afifi and Michael S Brown. Interactive white balancing for camera-rendered images. arXiv preprint arXiv:2009.12632, 2020.","title":"Interactive white balancing for camera-rendered images","authors":"Brown Afifi, Mahmoud Afifi, Michael S Brown","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Afifi et al., 2019a] Mahmoud Afifi, Brian Price, Scott Co- hen, and Michael S Brown. When color constancy goes wrong: Correcting improperly white-balanced images. In CVPR, 2019.","title":"When color constancy goes wrong: Correcting improperly white-balanced images","authors":"Afifi","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Afifi et al., 2019b] Mahmoud Afifi, Abhijith Punnappurath, Abdelrahman Abdelhamed, Hakki Can Karaimer, Abdul- lah Abuolaim, and Michael S Brown. Color tempera- ture tuning: Allowing accurate post-capture white-balance editing. In Color and Imaging Conference, volume 2019, pages 1-6. Society for Imaging Science and Technology, 2019.","title":"Color temperature tuning: Allowing accurate post-capture white-balance editing","authors":"Afifi","year":"2019","venue":"Color and Imaging Conference","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Afifi et al., 2020] Mahmoud Afifi, Abdelrahman Abdel- hamed, Abdullah Abuolaim, Abhijith Punnappurath, and Michael S Brown. Cie xyz net: Unprocessing im- ages for low-level computer vision tasks. arXiv preprint arXiv:2006.12709, 2020.","title":"Cie xyz net: Unprocessing images for low-level computer vision tasks","authors":"Mahmoud Afifi, Abdelrahman Abdelhamed, Abdullah Abuolaim, Abhijith Punnappurath, Michael S Brown","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Afifi et al., 2021] Mahmoud Afifi, Marcus A Brubaker, and Michael S Brown. Auto white-balance cor- rection for mixed-illuminant scenes. arXiv preprint arXiv:2109.08750, 2021.","title":"Auto white-balance correction for mixed-illuminant scenes","authors":"Mahmoud Afifi, Marcus A Brubaker, Michael S Brown","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Afifi, 2021] Mahmoud Afifi. Image color correction, en- hancement, and editing. arXiv preprint arXiv:2107.13117, 2021.","title":"Image color correction, enhancement, and editing","authors":"Mahmoud Afifi","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[An et al., 2021] Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, and Jiebo Luo. Artflow: Unbiased image style transfer via reversible neural flows. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 862-871, 2021.","title":"Artflow: Unbiased image style transfer via reversible neural flows","authors":"Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, Jiebo Luo","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Banić et al., 2017] Nikola Banić, Karlo Koščević, and Sven Lončarić. Unsupervised learning for color constancy. arXiv preprint arXiv:1712.00436, 2017.","title":"Unsupervised learning for color constancy","authors":"Nikola Banić, Karlo Koščević, Sven Lončarić","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Chakrabarti et al., 2014] Ayan Chakrabarti, Ying Xiong, Baochen Sun, Trevor Darrell, Daniel Scharstein, Todd Zickler, and Kate Saenko. Modeling radiometric uncer- tainty for vision with tone-mapped color images. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 36(11):2185-2198, 2014.","title":"Modeling radiometric uncertainty for vision with tone-mapped color images","authors":"Ayan Chakrabarti, Ying Xiong, Baochen Sun, Trevor Darrell, Daniel Scharstein, Todd Zickler, Kate Saenko","year":"2014","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Cheng et al., 2014] Dongliang Cheng, Dilip K Prasad, and Michael S Brown. Illuminant estimation for color con- stancy: why spatial-domain methods work and the role of the color distribution. JOSA A, 31(5):1049-1058, 2014.","title":"Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution","authors":"Dongliang Cheng, Dilip K Prasad, Michael S Brown","year":"2014","venue":"JOSA A","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Foster, 2011] David H Foster. Color constancy. Vision re- search, 51(7):674-700, 2011.","title":"Color constancy","authors":"H David, Foster","year":"2011","venue":"Vision research","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Gao et al., 2017] Shao-Bing Gao, Ming Zhang, Chao-Yi Li, and Yong-Jie Li. Improving color constancy by discount- ing the variation of camera spectral sensitivity. JOSA A, 34(8):1448-1462, 2017.","title":"Improving color constancy by discounting the variation of camera spectral sensitivity","authors":"Bing Shao, Ming Gao, Chao-Yi Zhang, Yong-Jie Li, Li","year":"2017","venue":"JOSA A","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Gijsenij and Gevers, 2007] Arjan Gijsenij and Theo Gevers. Color constancy using natural image statistics. In 2007 IEEE Conference on Computer Vision and Pattern Recog- nition, pages 1-8. IEEE, 2007.","title":"Color constancy using natural image statistics","authors":"Gevers Gijsenij, Arjan Gijsenij, Theo Gevers","year":"2007","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hong et al., 2001] Guowei Hong, M Ronnier Luo, and Pe- ter A Rhodes. A study of digital camera colorimetric char- acterization based on polynomial modeling. Color Re- search & Application: Endorsed by Inter-Society Color Council, The Colour Group (Great Britain), Canadian So- ciety for Color, Color Science Association of Japan, Dutch Society for the Study of Color, The Swedish Colour Centre Foundation, Colour Society of Australia, Centre Franc ¸ais de la Couleur, 26(1):76-84, 2001.","title":"Endorsed by Inter-Society Color Council, The Colour Group (Great Britain), Canadian Society for Color, Color Science Association of Japan, Dutch Society for the Study of Color, The Swedish Colour Centre Foundation, Colour Society of Australia","authors":"Guowei Hong, M Ronnier Luo, Peter A Rhodes","year":"2001","venue":"Centre Franc ¸ais de la Couleur","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Hu et al., 2017] Yuanming Hu, Baoyuan Wang, and Stephen Lin. Fc4: Fully convolutional color constancy with confidence-weighted pooling. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4085-4094, 2017.","title":"Fc4: Fully convolutional color constancy with confidence-weighted pooling","authors":"Yuanming Hu, Baoyuan Wang, Stephen Lin","year":"2017","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Huang and Belongie, 2017] Xun Huang and Serge Be- longie. Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE in- ternational conference on computer vision, pages 1501- 1510, 2017.","title":"Arbitrary style transfer in real-time with adaptive instance normalization","authors":"Belongie Huang","year":"2017","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Huang et al., 2020] Xinwei Huang, Bing Li, Shuai Li, Wen- juan Li, Weihua Xiong, Xuanwu Yin, Weiming Hu, and Hong Qin. Multi-cue semi-supervised color constancy with limited training samples. IEEE Transactions on Im- age Processing, 29:7875-7888, 2020.","title":"Multi-cue semi-supervised color constancy with limited training samples","authors":"Xinwei Huang, Bing Li, Shuai Li, Wenjuan Li, Weihua Xiong, Xuanwu Yin, Weiming Hu, Hong Qin","year":"2020","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":20,"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":21,"raw":"[Kingma and Dhariwal, 2018] Durk P Kingma and Prafulla Dhariwal. Glow: Generative flow with invertible 1x1 con- volutions. Advances in neural information processing sys- tems, 31, 2018.","title":"Glow: Generative flow with invertible 1x1 convolutions","authors":"Dhariwal ; Kingma, P Durk, Prafulla Kingma, Dhariwal","year":"2018","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lo et al., 2021] Yi-Chen Lo, Chia-Che Chang, Hsuan-Chao Chiu, Yu-Hao Huang, Chia-Ping Chen, Yu-Lin Chang, and Kevin Jou. Clcc: Contrastive learning for color constancy. arXiv preprint arXiv:2106.04989, 2021.","title":"Clcc: Contrastive learning for color constancy","authors":"Yi-Chen Lo, Chia-Che Chang, Hsuan-Chao Chiu, Yu-Hao Huang, Chia-Ping Chen, Yu-Lin Chang, Kevin Jou","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Ramanath et al., 2005] Rajeev Ramanath, Wesley E Snyder, Youngjun Yoo, and Mark S Drew. Color image processing pipeline. IEEE Signal Processing Magazine, 22(1):34-43, 2005.","title":"Color image processing pipeline","authors":"Rajeev Ramanath, Wesley E Snyder, Youngjun Yoo, Mark S Drew","year":"2005","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ronneberger et al., 2015] Olaf Ronneberger, Philipp Fis- cher, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer- assisted intervention, pages 234-241. Springer, 2015.","title":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation","authors":"Ronneberger","year":"2015","venue":"International Conference on Medical image computing and computerassisted intervention","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sharma et al., 2005] Gaurav Sharma, Wencheng Wu, and Edul N Dalal. The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and math- ematical observations. Color Research & Application, 30(1):21-30, 2005.","title":"The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations","authors":"Gaurav Sharma, Wencheng Wu, Edul N Dalal","year":"2005","venue":"Color Research & Application","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Song et al., 2021] Zeyu Song, Dongliang Chang, Zhanyu Ma, Xiaoxu Li, and Zheng-Hua Tan. Cc-loss: Channel correlation loss for image classification. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 7601-7608. IEEE, 2021.","title":"Cc-loss: Channel correlation loss for image classification","authors":"Song","year":"2020","venue":"25th International Conference on Pattern Recognition (ICPR)","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Stricker and Orengo, 1995] Markus Andreas Stricker and Markus Orengo. Similarity of color images. In Storage and retrieval for image and video databases III, volume 2420, pages 381-392. SPiE, 1995.","title":"Similarity of color images","authors":"Orengo ; Stricker, Andreas Markus, Markus Stricker, Orengo","year":"1995","venue":"Storage and retrieval for image and video databases III","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tang et al., 2022] Yuxiang Tang, Xuejing Kang, Chunxiao Li, Zhaowen Lin, and Anlong Ming. Transfer learning for color constancy via statistic perspective. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 2361-2369, 2022.","title":"Transfer learning for color constancy via statistic perspective","authors":"Yuxiang Tang, Xuejing Kang, Chunxiao Li, Zhaowen Lin, Anlong Ming","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xu et al., 2021] Qinwei Xu, Ruipeng Zhang, Ya Zhang, Yanfeng Wang, and Qi Tian. A fourier-based frame- work for domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14383-14392, 2021.","title":"A fourier-based framework for domain generalization","authors":"Xu","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2022] Zhifeng Zhang, Xuejing Kang, and An- long Ming. Domain adversarial learning for color con- stancy. In Lud De Raedt, editor, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 1693-1699. International Joint Conferences on Artificial Intelligence Organization, 7 2022. Main Track.","title":"Domain adversarial learning for color constancy","authors":"Zhifeng Zhang, Xuejing Kang, Anlong Ming","year":"2022","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22","doi":null,"url":null,"internal_url":"/proceedings/2022/236"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}