{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T15:55:32Z","timestamp":1774626932712,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":97,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611834","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"6959-6968","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Controllable Face Sketch-Photo Synthesis with Flexible Generative Priors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-8424","authenticated-orcid":false,"given":"Kun","family":"Cheng","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4179-7701","authenticated-orcid":false,"given":"Mingrui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1435-489X","authenticated-orcid":false,"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7069-7486","authenticated-orcid":false,"given":"Guozhang","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3270-841X","authenticated-orcid":false,"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1443-0776","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing University of Post and Telecommunications, Chongqing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00664"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jihye Back Seungkwon Kim and Namhyuk Ahn. 2022. WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylization. In SIGGRAPH Asia 2022 Technical Communications. 1--4.","DOI":"10.1145\/3550340.3564226"},{"key":"e_1_3_2_1_6_1","volume-title":"Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"MaskSketch: Unpaired Structure-guided Masked Image Generation. arXiv preprint arXiv:2302.05496","author":"Bashkirova Dina","year":"2023","unstructured":"Dina Bashkirova, Jose Lezama, Kihyuk Sohn, Kate Saenko, and Irfan Essa. 2023. MaskSketch: Unpaired Structure-guided Masked Image Generation. arXiv preprint arXiv:2302.05496 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"e_1_3_2_1_9_1","volume-title":"Asian Conference on Computer Vision. Springer, 216--231","author":"Chen Chaofeng","year":"2018","unstructured":"Chaofeng Chen, Wei Liu, Xiao Tan, and Kwan-Yee K Wong. 2018. Semi-supervised learning for face sketch synthesis in the wild. In Asian Conference on Computer Vision. Springer, 216--231."},{"key":"e_1_3_2_1_10_1","volume-title":"Tel Aviv","author":"Chen Yu-Jie","year":"2022","unstructured":"Yu-Jie Chen, Shin-I Cheng, Wei-Chen Chiu, Hung-Yu Tseng, and Hsin-Ying Lee. 2022. Vector Quantized Image-to-Image Translation. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XVI. Springer, 440--456."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"e_1_3_2_1_13_1","volume-title":"Tel Aviv","author":"Chong Min Jin","year":"2022","unstructured":"Min Jin Chong and David Forsyth. 2022. Jojogan: One shot face stylization. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XVI. Springer, 128--152."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Fan Deng-Ping Huang Ziling Zheng Peng Liu Hong Qin Xuebin and Van Gool Luc. 2022. Facial-Sketch Synthesis: A New Challenge.","DOI":"10.1007\/s11633-022-1349-9"},{"key":"e_1_3_2_1_15_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, Vol. 34 (2021), 8780--8794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Stylegan-nada: Clip-guided domain adaptation of image generators. arXiv preprint arXiv:2108.00946","author":"Gal Rinon","year":"2021","unstructured":"Rinon Gal, Or Patashnik, Haggai Maron, Gal Chechik, and Daniel Cohen-Or. 2021. Stylegan-nada: Clip-guided domain adaptation of image generators. arXiv preprint arXiv:2108.00946 (2021)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061286"},{"key":"e_1_3_2_1_19_1","volume-title":"Tel Aviv","author":"Gu Yuchao","year":"2022","unstructured":"Yuchao Gu, Xintao Wang, Liangbin Xie, Chao Dong, Gen Li, Ying Shan, and Ming-Ming Cheng. 2022. Vqfr: Blind face restoration with vector-quantized dictionary and parallel decoder. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XVIII. Springer, 126--143."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_21_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_22_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6840--6851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3065230"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. NeurIPS.","author":"H\u00e4rk\u00f6nen Erik","year":"2020","unstructured":"Erik H\u00e4rk\u00f6nen, Aaron Hertzmann, Jaakko Lehtinen, and Sylvain Paris. 2020. GANSpace: Discovering Interpretable GAN Controls. In Proc. NeurIPS."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_28_1","volume-title":"Masked and Adaptive Transformer for Exemplar Based Image Translation. arXiv preprint arXiv:2303.17123","author":"Jiang Chang","year":"2023","unstructured":"Chang Jiang, Fei Gao, Biao Ma, Yuhao Lin, Nannan Wang, and Gang Xu. 2023. Masked and Adaptive Transformer for Exemplar Based Image Translation. arXiv preprint arXiv:2303.17123 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196","author":"Karras Tero","year":"2017","unstructured":"Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2017. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)."},{"key":"e_1_3_2_1_30_1","first-page":"852","article-title":"Alias-free generative adversarial networks","volume":"34","author":"Karras Tero","year":"2021","unstructured":"Tero Karras, Miika Aittala, Samuli Laine, Erik H\u00e4rk\u00f6nen, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2021. Alias-free generative adversarial networks. Advances in Neural Information Processing Systems, Vol. 34 (2021), 852--863.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_33_1","volume-title":"Cross-Domain Style Mixing for Face Cartoonization. arXiv preprint arXiv:2205.12450","author":"Kim Seungkwon","year":"2022","unstructured":"Seungkwon Kim, Chaeheon Gwak, Dohyun Kim, Kwangho Lee, Jihye Back, Namhyuk Ahn, and Daesik Kim. 2022. Cross-Domain Style Mixing for Face Cartoonization. arXiv preprint arXiv:2205.12450 (2022)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00413"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3263886"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_37_1","first-page":"29710","article-title":"Blendgan: Implicitly gan blending for arbitrary stylized face generation","volume":"34","author":"Liu Mingcong","year":"2021","unstructured":"Mingcong Liu, Qiang Li, Zekui Qin, Guoxin Zhang, Pengfei Wan, and Wen Zheng. 2021. Blendgan: Implicitly gan blending for arbitrary stylized face generation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 29710--29722.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"Unsupervised image-to-image translation networks. Advances in neural information processing systems","author":"Liu Ming-Yu","year":"2017","unstructured":"Ming-Yu Liu, Thomas Breuel, and Jan Kautz. 2017. Unsupervised image-to-image translation networks. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2005.39","volume-title":"2005 IEEE Computer Society conference on computer vision and pattern recognition (CVPR'05)","volume":"1","author":"Liu Qingshan","year":"2005","unstructured":"Qingshan Liu, Xiaoou Tang, Hongliang Jin, Hanqing Lu, and Songde Ma. 2005. A nonlinear approach for face sketch synthesis and recognition. In 2005 IEEE Computer Society conference on computer vision and pattern recognition (CVPR'05), Vol. 1. IEEE, 1005--1010."},{"key":"e_1_3_2_1_40_1","volume-title":"Tel Aviv","author":"Liu Songhua","year":"2022","unstructured":"Songhua Liu, Jingwen Ye, Sucheng Ren, and Xinchao Wang. 2022. Dynast: Dynamic sparse transformer for exemplar-guided image generation. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XVI. Springer, 72--90."},{"key":"e_1_3_2_1_41_1","volume-title":"DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation. arXiv preprint arXiv:2303.06285","author":"Lyu Yueming","year":"2023","unstructured":"Yueming Lyu, Tianwei Lin, Fu Li, Dongliang He, Jing Dong, and Tieniu Tan. 2023. DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation. arXiv preprint arXiv:2303.06285 (2023)."},{"key":"e_1_3_2_1_42_1","unstructured":"Aleix Martinez and Robert Benavente. 1998. The AR Face Database: CVC Technical Report 24. (1998)."},{"key":"e_1_3_2_1_43_1","volume-title":"International Conference on Learning Representations.","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_44_1","volume-title":"Second international conference on audio and video-based biometric person authentication","volume":"964","author":"Messer Kieron","year":"1999","unstructured":"Kieron Messer, Jiri Matas, Josef Kittler, Juergen Luettin, Gilbert Maitre, et al. 1999. XM2VTSDB: The extended M2VTS database. In Second international conference on audio and video-based biometric person authentication, Vol. 964. Citeseer, 965--966."},{"key":"e_1_3_2_1_45_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_1_46_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_1_49_1","volume-title":"Resolution dependent gan interpolation for controllable image synthesis between domains. arXiv preprint arXiv:2010.05334","author":"Pinkney Justin NM","year":"2020","unstructured":"Justin NM Pinkney and Doron Adler. 2020. Resolution dependent gan interpolation for controllable image synthesis between domains. arXiv preprint arXiv:2010.05334 (2020)."},{"key":"e_1_3_2_1_50_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_52_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Daniel Roich Ron Mokady Amit H Bermano and Daniel Cohen-Or. 2021. Pivotal Tuning for Latent-based Editing of Real Images. ACM Trans. Graph. (2021).","DOI":"10.1145\/3544777"},{"key":"e_1_3_2_1_55_1","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv: 2112.10752 [cs.CV]"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_58_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_59_1","volume-title":"Interfacegan: Interpreting the disentangled face representation learned by gans","author":"Shen Yujun","year":"2020","unstructured":"Yujun Shen, Ceyuan Yang, Xiaoou Tang, and Bolei Zhou. 2020. Interfacegan: Interpreting the disentangled face representation learned by gans. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 4 (2020), 2004--2018."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459771"},{"key":"e_1_3_2_1_62_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038008"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/946247.946604"},{"key":"e_1_3_2_1_65_1","volume-title":"Designing an Encoder for StyleGAN Image Manipulation. arXiv preprint arXiv:2102.02766","author":"Tov Omer","year":"2021","unstructured":"Omer Tov, Yuval Alaluf, Yotam Nitzan, Or Patashnik, and Daniel Cohen-Or. 2021. Designing an Encoder for StyleGAN Image Manipulation. arXiv preprint arXiv:2102.02766 (2021)."},{"key":"e_1_3_2_1_66_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00022"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.11.008"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651375"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0645-9"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.06.012"},{"key":"e_1_3_2_1_72_1","unstructured":"Tengfei Wang Ting Zhang Bo Zhang Hao Ouyang Dong Chen Qifeng Chen and Fang Wen. 2022c. Pretraining is All You Need for Image-to-Image Translation. In arXiv."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01109"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01113"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"e_1_3_2_1_76_1","volume-title":"Face photo-sketch synthesis and recognition","author":"Wang Xiaogang","year":"2008","unstructured":"Xiaogang Wang and Xiaoou Tang. 2008. Face photo-sketch synthesis and recognition. IEEE transactions on pattern analysis and machine intelligence, Vol. 31, 11 (2008), 1955--1967."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00070"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00073"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01100"},{"key":"e_1_3_2_1_81_1","volume-title":"Toward realistic face photo-sketch synthesis via composition-aided GANs","author":"Yu Jun","year":"2020","unstructured":"Jun Yu, Xingxin Xu, Fei Gao, Shengjie Shi, Meng Wang, Dacheng Tao, and Qingming Huang. 2020. Toward realistic face photo-sketch synthesis via composition-aided GANs. IEEE transactions on cybernetics (2020)."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3229614"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01478"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01040"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. arxiv: 2302.05543 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_86_1","volume-title":"FSIM: A feature similarity index for image quality assessment","author":"Zhang Lin","year":"2011","unstructured":"Lin Zhang, Lei Zhang, Xuanqin Mou, and David Zhang. 2011. FSIM: A feature similarity index for image quality assessment. IEEE transactions on Image Processing, Vol. 20, 8 (2011), 2378--2386."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2422578"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247788"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01130"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"crossref","unstructured":"Mingrui Zhu Changcheng Liang Nannan Wang Xiaoyu Wang Zhifeng Li and Xinbo Gao. 2021. A Sketch-Transformer Network for Face Photo-Sketch Synthesis.. In IJCAI. 1352--1358.","DOI":"10.24963\/ijcai.2021\/187"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/500"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"crossref","unstructured":"Mingrui Zhu Nannan Wang Xinbo Gao Jie Li and Zhifeng Li. 2019b. Face Photo-Sketch Synthesis via Knowledge Transfer.. In IJCAI. 1048--1054.","DOI":"10.24963\/ijcai.2019\/147"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"e_1_3_2_1_97_1","unstructured":"zllrunning. 2019. face-parsing.PyTorch. https:\/\/github.com\/zllrunning\/face-parsing.PyTorch."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611834","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:57:50Z","timestamp":1755820670000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611834"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":97,"alternative-id":["10.1145\/3581783.3611834","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611834","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}