{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:58:41Z","timestamp":1778083121321,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,23]],"date-time":"2023-07-23T00:00:00Z","timestamp":1690070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,23]]},"DOI":"10.1145\/3588432.3591558","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T13:34:52Z","timestamp":1689773692000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Diffusion Image Analogies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0694-2096","authenticated-orcid":false,"given":"Ad\u00e9la","family":"\u0160ubrtov\u00e1","sequence":"first","affiliation":[{"name":"CTU in Prague, FEE, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9664-7786","authenticated-orcid":false,"given":"Michal","family":"Luk\u00e1\u010d","sequence":"additional","affiliation":[{"name":"Adobe Research, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2181-5917","authenticated-orcid":false,"given":"Jan","family":"\u010cech","sequence":"additional","affiliation":[{"name":"CTU in Prague, FEE, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3254-0290","authenticated-orcid":false,"given":"David","family":"Futschik","sequence":"additional","affiliation":[{"name":"CTU in Prague, FEE, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6783-1795","authenticated-orcid":false,"given":"Eli","family":"Shechtman","sequence":"additional","affiliation":[{"name":"Adobe Research, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6145-5151","authenticated-orcid":false,"given":"Daniel","family":"S\u00fdkora","sequence":"additional","affiliation":[{"name":"CTU in Prague, FEE, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,23]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of Symposium on Interactive 3D graphics. 217\u2013226","author":"Ashikhmin Michael","year":"2001","unstructured":"Michael Ashikhmin . 2001 . Synthesizing Natural Textures . In Proceedings of Symposium on Interactive 3D graphics. 217\u2013226 . Michael Ashikhmin. 2001. Synthesizing Natural Textures. In Proceedings of Symposium on Interactive 3D graphics. 217\u2013226."},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 18208\u201318209","author":"Avrahami Omri","year":"2022","unstructured":"Omri Avrahami , Dani Lischinski , and Ohad Fried . 2022 . Blended Diffusion for Text-driven Editing of Natural Images . In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 18208\u201318209 . Omri Avrahami, Dani Lischinski, and Ohad Fried. 2022. Blended Diffusion for Text-driven Editing of Natural Images. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 18208\u201318209."},{"key":"e_1_3_2_2_3_1","unstructured":"Amir Bar Yossi Gandelsman Trevor Darrell Amir Globerson and Alexei\u00a0A Efros. 2022. Visual Prompting via Image Inpainting. In Advances in Neural Information Processing Systems. Amir Bar Yossi Gandelsman Trevor Darrell Amir Globerson and Alexei\u00a0A Efros. 2022. Visual Prompting via Image Inpainting. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461929"},{"key":"e_1_3_2_2_6_1","unstructured":"Albert\u00a0S Berahas Jorge Nocedal and Martin Takac. 2016. A Multi-Batch L-BFGS Method for Machine Learning. In Advances in Neural Information Processing Systems. Albert\u00a0S Berahas Jorge Nocedal and Martin Takac. 2016. A Multi-Batch L-BFGS Method for Machine Learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Brooks Tim","year":"2023","unstructured":"Tim Brooks , Aleksander Holynski , and Alexei\u00a0 A. Efros . 2023 . InstructPix2Pix: Learning to Follow Image Editing Instructions . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Tim Brooks, Aleksander Holynski, and Alexei\u00a0A. Efros. 2023. InstructPix2Pix: Learning to Follow Image Editing Instructions. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_8_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel Ziegler Jeffrey Wu Clemens Winter Chris Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems. 1877\u20131901. Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel Ziegler Jeffrey Wu Clemens Winter Chris Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems. 1877\u20131901."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of IEEE International Conference on Computer Vision. 9650\u20139660","author":"Caron Mathilde","year":"2021","unstructured":"Mathilde Caron , Hugo Touvron , Ishan Misra , Herve Jegou , Julien Mairal , Piotr Bojanowski , and Armand Joulin . 2021 . Emerging properties in self-supervised vision transformers . In Proceedings of IEEE International Conference on Computer Vision. 9650\u20139660 . Mathilde Caron, Hugo Touvron, Ishan Misra, Herve Jegou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. 2021. Emerging properties in self-supervised vision transformers. In Proceedings of IEEE International Conference on Computer Vision. 9650\u20139660."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2699641"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925948"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073660"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/38.988747"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the ACM\/EG Expressive Symposium. 33\u201342","author":"Futschik David","year":"2019","unstructured":"David Futschik , Menglei Chai , Chen Cao , Chongyang Ma , Aleksei Stoliar , Sergey Korolev , Sergey Tulyakov , Michal Ku\u010dera , and Daniel S\u00fdkora . 2019 . Real-Time Patch-Based Stylization of Portraits Using Generative Adversarial Network . In Proceedings of the ACM\/EG Expressive Symposium. 33\u201342 . David Futschik, Menglei Chai, Chen Cao, Chongyang Ma, Aleksei Stoliar, Sergey Korolev, Sergey Tulyakov, Michal Ku\u010dera, and Daniel S\u00fdkora. 2019. Real-Time Patch-Based Stylization of Portraits Using Generative Adversarial Network. In Proceedings of the ACM\/EG Expressive Symposium. 33\u201342."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.142655"},{"key":"e_1_3_2_2_16_1","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit\u00a0H. Bermano Gal Chechik and Daniel Cohen-Or. 2022a. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In arXiv:2208.01618. Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit\u00a0H. Bermano Gal Chechik and Daniel Cohen-Or. 2022a. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In arXiv:2208.01618."},{"key":"e_1_3_2_2_17_1","first-page":"141","article-title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","volume":"41","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal , Or Patashnik , Haggai Maron , Amit\u00a0 H. Bermano , Gal Chechik , and Daniel Cohen-Or . 2022 b. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators . ACM Transactions on Graphics 41 , 4 (2022), 141 . Rinon Gal, Or Patashnik, Haggai Maron, Amit\u00a0H. Bermano, Gal Chechik, and Daniel Cohen-Or. 2022b. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators. ACM Transactions on Graphics 41, 4 (2022), 141.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_2_19_1","unstructured":"Amir Hertz Ron Mokady Jay Tenenbaum Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. In arXiv:2208.01626. Amir Hertz Ron Mokady Jay Tenenbaum Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. In arXiv:2208.01626."},{"key":"e_1_3_2_2_20_1","volume-title":"Image Analogies. In SIGGRAPH Conference Proceedings. 327\u2013340","author":"Hertzmann Aaron","year":"2001","unstructured":"Aaron Hertzmann , Charles\u00a0 E. Jacobs , Nuria Oliver , Brian Curless , and David\u00a0 H. Salesin . 2001 . Image Analogies. In SIGGRAPH Conference Proceedings. 327\u2013340 . Aaron Hertzmann, Charles\u00a0E. Jacobs, Nuria Oliver, Brian Curless, and David\u00a0H. Salesin. 2001. Image Analogies. In SIGGRAPH Conference Proceedings. 327\u2013340."},{"key":"e_1_3_2_2_21_1","first-page":"1","article-title":"Cascaded Diffusion Models for High Fidelity Image Generation","volume":"23","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho , Chitwan Saharia , William Chan , David\u00a0 J. Fleet , Mohammad Norouzi , and Tim Salimans . 2022 . Cascaded Diffusion Models for High Fidelity Image Generation . Journal of Machine Learning Research 23 , 47 (2022), 1 \u2013 33 . Jonathan Ho, Chitwan Saharia, William Chan, David\u00a0J. Fleet, Mohammad Norouzi, and Tim Salimans. 2022. Cascaded Diffusion Models for High Fidelity Image Generation. Journal of Machine Learning Research 23, 47 (2022), 1\u201333.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 5967\u20135976","author":"Isola Phillip","year":"2017","unstructured":"Phillip Isola , Jun-Yan Zhu , Tinghui Zhou , and Alexei\u00a0 A. Efros . 2017 . Image-to-Image Translation with Conditional Adversarial Networks . In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 5967\u20135976 . Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei\u00a0A. Efros. 2017. Image-to-Image Translation with Conditional Adversarial Networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 5967\u20135976."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323006"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Kawar Bahjat","year":"2023","unstructured":"Bahjat Kawar , Shiran Zada , Oran Lang , Omer Tov , Huiwen Chang , Tali Dekel , Inbar Mosseri , and Michal Irani . 2023 . Imagic: Text-Based Real Image Editing with Diffusion Models . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, and Michal Irani. 2023. Imagic: Text-Based Real Image Editing with Diffusion Models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01029"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Kwon Gihyun","year":"2023","unstructured":"Gihyun Kwon and Jong\u00a0Chul Ye . 2023 . Diffusion-based Image Translation using disentangled style and content representation . In Proceedings of International Conference on Learning Representations. Gihyun Kwon and Jong\u00a0Chul Ye. 2023. Diffusion-based Image Translation using disentangled style and content representation. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_2_27_1","unstructured":"LambdaLabsML. 2022. Lambda Diffusers - Stable Diffusion Image Variations. https:\/\/github.com\/LambdaLabsML\/lambda-diffusers LambdaLabsML. 2022. Lambda Diffusers - Stable Diffusion Image Variations. https:\/\/github.com\/LambdaLabsML\/lambda-diffusers"},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2479\u20132486","author":"Li Chuan","year":"2016","unstructured":"Chuan Li and Michael Wand . 2016 . Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis . In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2479\u20132486 . Chuan Li and Michael Wand. 2016. Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2479\u20132486."},{"key":"e_1_3_2_2_29_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning. 12888\u201312900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li , Dongxu Li , Caiming Xiong , and Steven Hoi . 2022 . BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning. 12888\u201312900 . Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning. 12888\u201312900."},{"key":"e_1_3_2_2_30_1","unstructured":"Yijun Li Chen Fang Jimei Yang Zhaowen Wang Xin Lu and Ming-Hsuan Yang. 2017. Universal Style Transfer via Feature Transforms. In Advances in Neural Information Processing Systems. 385\u2013395. Yijun Li Chen Fang Jimei Yang Zhaowen Wang Xin Lu and Ming-Hsuan Yang. 2017. Universal Style Transfer via Feature Transforms. In Advances in Neural Information Processing Systems. 385\u2013395."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073683"},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 10551\u201310560","author":"Liu Ming-Yu","year":"2019","unstructured":"Ming-Yu Liu , Xun Huang , Arun Mallya , Tero Karras , Timo Aila , Jaakko Lehtinen , and Jan Kautz . 2019 . Few-Shot Unsupervised Image-to-Image Translation . In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 10551\u201310560 . Ming-Yu Liu, Xun Huang, Arun Mallya, Tero Karras, Timo Aila, Jaakko Lehtinen, and Jan Kautz. 2019. Few-Shot Unsupervised Image-to-Image Translation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 10551\u201310560."},{"key":"e_1_3_2_2_33_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter . 2019 . Decoupled Weight Decay Regularization. In International Conference on Learning Representations. Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng , Yutong He , Yang Song , Jiaming Song , Jiajun Wu , Jun-Yan Zhu , and Stefano Ermon . 2022 . SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations . In Proceedings of International Conference on Learning Representations. Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Mikolov Tom\u00e1\u0161","year":"2013","unstructured":"Tom\u00e1\u0161 Mikolov , Kai Chen , Greg Corrado , and Jeffrey Dean . 2013 . Efficient Estimation of Word Representations in Vector Space . In Proceedings of International Conference on Learning Representations. Tom\u00e1\u0161 Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Ron Mokady Amir Hertz Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2022. Null-text Inversion for Editing Real Images using Guided Diffusion Models. In arXiv:2211.09794. Ron Mokady Amir Hertz Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2022. Null-text Inversion for Editing Real Images using Guided Diffusion Models. In arXiv:2211.09794.","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of International Conference on Machine Learning. 16784\u201316804","author":"Nichol Alex","year":"2022","unstructured":"Alex Nichol , Prafulla Dhariwal , Aditya Ramesh , Pranav Shyam , Pamela Mishkin , Bob McGrew , Ilya Sutskever , and Mark Chen . 2022 . GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models . In Proceedings of International Conference on Machine Learning. 16784\u201316804 . Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In Proceedings of International Conference on Machine Learning. 16784\u201316804."},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of European Conference on Computer Vision.","author":"Park Taesung","year":"2020","unstructured":"Taesung Park , Alexei\u00a0 A. Efros , Richard Zhang , and Jun-Yan Zhu . 2020 . Contrastive Learning for Unpaired Image-to-Image Translation . In Proceedings of European Conference on Computer Vision. Taesung Park, Alexei\u00a0A. Efros, Richard Zhang, and Jun-Yan Zhu. 2020. Contrastive Learning for Unpaired Image-to-Image Translation. In Proceedings of European Conference on Computer Vision."},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of IEEE International Conference on Computer Vision. 2085\u20132094","author":"Patashnik Or","year":"2021","unstructured":"Or Patashnik , Zongze Wu , Eli Shechtman , Daniel Cohen-Or , and Dani Lischinski . 2021 . StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery . In Proceedings of IEEE International Conference on Computer Vision. 2085\u20132094 . Or Patashnik, Zongze Wu, Eli Shechtman, Daniel Cohen-Or, and Dani Lischinski. 2021. StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery. In Proceedings of IEEE International Conference on Computer Vision. 2085\u20132094."},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning. 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford , Jong\u00a0Wook Kim , Chris Hallacy , Aditya Ramesh , Gabriel Goh , Sandhini Agarwal , Girish Sastry , Amanda Askell , Pamela Mishkin , Jack Clark , Gretchen Krueger , and Ilya Sutskever . 2021 . Learning Transferable Visual Models From Natural Language Supervision . In Proceedings of the 38th International Conference on Machine Learning. 8748\u20138763 . Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_2_2_41_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019). Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_2_42_1","unstructured":"Aditya Ramesh. 2022. How DALL\u00b7E 2 Works. http:\/\/adityaramesh.com\/posts\/dalle2\/dalle2.html Aditya Ramesh. 2022. How DALL\u00b7E 2 Works. http:\/\/adityaramesh.com\/posts\/dalle2\/dalle2.html"},{"key":"e_1_3_2_2_43_1","volume-title":"Proceedings of Eurographics Symposium on Rendering. 371\u2013376","author":"Ritter Lincoln","year":"2006","unstructured":"Lincoln Ritter , Wilmot Li , Brian Curless , Maneesh Agrawala , and David Salesin . 2006 . Painting With Texture . In Proceedings of Eurographics Symposium on Rendering. 371\u2013376 . Lincoln Ritter, Wilmot Li, Brian Curless, Maneesh Agrawala, and David Salesin. 2006. Painting With Texture. In Proceedings of Eurographics Symposium on Rendering. 371\u2013376."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_45_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Ruiz Nataniel","year":"2023","unstructured":"Nataniel Ruiz , Yuanzhen Li , Varun Jampani , Yael Pritch , Michael Rubinstein , and Kfir Aberman . 2023 . Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2023. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_46_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2014)."},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song , Chenlin Meng , and Stefano Ermon . 2021 . Denoising Diffusion Implicit Models . In Proceedings of International Conference on Learning Representations. Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_2_48_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17897\u201317907","author":"Tewel Yoad","year":"2022","unstructured":"Yoad Tewel , Yoav Shalev , Idan Schwartz , and Lior Wolf . 2022 . ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17897\u201317907 . Yoad Tewel, Yoav Shalev, Idan Schwartz, and Lior Wolf. 2022. ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17897\u201317907."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2020.01.002"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392453"},{"key":"e_1_3_2_2_51_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10748\u201310757","author":"Tumanyan Narek","year":"2022","unstructured":"Narek Tumanyan , Omer Bar-Tal , Shai Bagon , and Tali Dekel . 2022 . Splicing ViT Features for Semantic Appearance Transfer . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10748\u201310757 . Narek Tumanyan, Omer Bar-Tal, Shai Bagon, and Tali Dekel. 2022. Splicing ViT Features for Semantic Appearance Transfer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10748\u201310757."},{"key":"e_1_3_2_2_52_1","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 5143\u20135153","author":"Zhang Pan","year":"2020","unstructured":"Pan Zhang , Bo Zhang , Dong Chen , Lu Yuan , and Fang Wen . 2020 . Cross-domain Correspondence Learning for Exemplar-based Image Translation . In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 5143\u20135153 . Pan Zhang, Bo Zhang, Dong Chen, Lu Yuan, and Fang Wen. 2020. Cross-domain Correspondence Learning for Exemplar-based Image Translation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 5143\u20135153."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13119"},{"key":"e_1_3_2_2_54_1","volume-title":"Proceedings of IEEE International Conference on Computer Vision. 2242\u20132251","author":"Zhu Jun-Yan","year":"2017","unstructured":"Jun-Yan Zhu , Taesung Park , Phillip Isola , and Alexei\u00a0 A. Efros . 2017 . Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks . In Proceedings of IEEE International Conference on Computer Vision. 2242\u20132251 . Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei\u00a0A. Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In Proceedings of IEEE International Conference on Computer Vision. 2242\u20132251."}],"event":{"name":"SIGGRAPH '23: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Los Angeles CA USA","acronym":"SIGGRAPH '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588432.3591558","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:11Z","timestamp":1750178831000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588432.3591558"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,23]]},"references-count":54,"alternative-id":["10.1145\/3588432.3591558","10.1145\/3588432"],"URL":"https:\/\/doi.org\/10.1145\/3588432.3591558","relation":{},"subject":[],"published":{"date-parts":[[2023,7,23]]},"assertion":[{"value":"2023-07-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}