{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:02:41Z","timestamp":1784268161416,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"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":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657525","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["LOOSECONTROL: Lifting ControlNet for Generalized Depth Conditioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7668-4424","authenticated-orcid":false,"given":"Shariq Farooq","family":"Bhat","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST), Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2597-0914","authenticated-orcid":false,"given":"Niloy","family":"Mitra","sequence":"additional","affiliation":[{"name":"University College London (UCL), United Kingdom and Adobe Research, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0627-9746","authenticated-orcid":false,"given":"Peter","family":"Wonka","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST), Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"eDiff-I: Text-to-Image Diffusion Models with Ensemble of Expert Denoisers. arXiv preprint arXiv:2211.01324","author":"Balaji Yogesh","year":"2022","unstructured":"Yogesh Balaji, Seungjun Nah, Xun Huang, Arash Vahdat, Jiaming Song, Qinsheng Zhang, Karsten Kreis, Miika Aittala, Timo Aila, Samuli Laine, Bryan Catanzaro, Tero Karras, and Ming-Yu Liu. 2022. eDiff-I: Text-to-Image Diffusion Models with Ensemble of Expert Denoisers. arXiv preprint arXiv:2211.01324 (2022)."},{"key":"e_1_3_2_2_2_1","volume-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288","author":"Bhat Shariq\u00a0Farooq","year":"2023","unstructured":"Shariq\u00a0Farooq Bhat, Reiner Birkl, Diana Wofk, Peter Wonka, and Matthias M\u00fcller. 2023. Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)."},{"key":"e_1_3_2_2_3_1","volume-title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","author":"Cao Z.","year":"2019","unstructured":"Z. Cao, G. Hidalgo Martinez, T. Simon, S. Wei, and Y.\u00a0A. Sheikh. 2019. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Zhe Cao Tomas Simon Shih-En Wei and Yaser Sheikh. 2017. Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. In CVPR.","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Hansheng Chen Jiatao Gu Anpei Chen Wei Tian Zhuowen Tu Lingjie Liu and Hao Su. 2023. Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction. In ICCV. https:\/\/arxiv.org\/abs\/2304.06714","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Gene Chou Yuval Bahat and Felix Heide. 2023. Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions. arxiv:2211.13757 [cs]","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"e_1_3_2_2_7_1","volume-title":"Diffedit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427","author":"Couairon Guillaume","year":"2022","unstructured":"Guillaume Couairon, Jakob Verbeek, Holger Schwenk, and Matthieu Cord. 2022. Diffedit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)."},{"key":"e_1_3_2_2_8_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems 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 34 (2021), 8780\u20138794."},{"key":"e_1_3_2_2_9_1","volume-title":"Hyperdiffusion: Generating implicit neural fields with weight-space diffusion. arXiv preprint arXiv:2303.17015","author":"Erko\u00e7 Ziya","year":"2023","unstructured":"Ziya Erko\u00e7, Fangchang Ma, Qi Shan, Matthias Nie\u00dfner, and Angela Dai. 2023. Hyperdiffusion: Generating implicit neural fields with weight-space diffusion. arXiv preprint arXiv:2303.17015 (2023). https:\/\/arxiv.org\/abs\/2303.17015"},{"key":"e_1_3_2_2_10_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\u00a0H 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_2_11_1","volume-title":"Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models. arXiv preprint arXiv:2303.11073","author":"Haas Ren\u00e9","year":"2023","unstructured":"Ren\u00e9 Haas, Inbar Huberman-Spiegelglas, Rotem Mulayoff, and Tomer Michaeli. 2023. Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models. arXiv preprint arXiv:2303.11073 (2023)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Jack Hessel Ari Holtzman Maxwell Forbes Ronan\u00a0Le Bras and Yejin Choi. 2022. CLIPScore: A Reference-free Evaluation Metric for Image Captioning. arxiv:2104.08718\u00a0[cs.CV]","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_2_13_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 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 33 (2020), 6840\u20136851."},{"key":"e_1_3_2_2_14_1","volume-title":"Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778","author":"Huang Lianghua","year":"2023","unstructured":"Lianghua Huang, Di Chen, Yu Liu, Yujun Shen, Deli Zhao, and Jingren Zhou. 2023. Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555394"},{"key":"e_1_3_2_2_16_1","volume-title":"HoloFusion: Towards Photo-realistic 3D Generative Modeling. ICCV","author":"Karnewar Animesh","year":"2023","unstructured":"Animesh Karnewar, Niloy\u00a0J Mitra, Andrea Vedaldi, and David Novotny. 2023. HoloFusion: Towards Photo-realistic 3D Generative Modeling. ICCV (2023)."},{"key":"e_1_3_2_2_17_1","volume-title":"Text2video-zero: Text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439","author":"Khachatryan Levon","year":"2023","unstructured":"Levon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel, Zhangyang Wang, Shant Navasardyan, and Humphrey Shi. 2023. Text2video-zero: Text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439 (2023)."},{"key":"e_1_3_2_2_18_1","volume-title":"Segment anything. arXiv preprint arXiv:2304.02643","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander\u00a0C Berg, Wan-Yen Lo, 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023)."},{"key":"e_1_3_2_2_19_1","volume-title":"Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960","author":"Kwon Mingi","year":"2022","unstructured":"Mingi Kwon, Jaeseok Jeong, and Youngjung Uh. 2022. Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960 (2022)."},{"key":"e_1_3_2_2_20_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023a. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_2_24_1","volume-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453","author":"Mou Chong","year":"2023","unstructured":"Chong Mou, Xintao Wang, Liangbin Xie, Jian Zhang, Zhongang Qi, Ying Shan, and Xiaohu Qie. 2023. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)."},{"key":"e_1_3_2_2_25_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_2_26_1","volume-title":"International Conference on Machine Learning. PMLR, 8162\u20138171","author":"Nichol Alexander\u00a0Quinn","year":"2021","unstructured":"Alexander\u00a0Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning. PMLR, 8162\u20138171."},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_2_2_28_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2","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 1, 2 (2022), 3."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_2_31_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\u00a0L Denton, Kamyar Ghasemipour, Raphael Gontijo\u00a0Lopes, Burcu Karagol\u00a0Ayan, Tim Salimans, 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems 35 (2022), 36479\u201336494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Nathan Silberman Derek Hoiem Pushmeet Kohli and Rob Fergus. 2012. Indoor Segmentation and Support Inference from RGBD Images. In ECCV.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Tomas Simon Hanbyul Joo Iain Matthews and Yaser Sheikh. 2017. Hand Keypoint Detection in Single Images using Multiview Bootstrapping. In CVPR.","DOI":"10.1109\/CVPR.2017.494"},{"key":"e_1_3_2_2_35_1","volume-title":"Key-Locked Rank One Editing for Text-to-Image Personalization. ACM SIGGRAPH 2023 Conference Proceedings","author":"Tewel Yoad","year":"2023","unstructured":"Yoad Tewel, Rinon Gal, Gal Chechik, and Yuval Atzmon. 2023. Key-Locked Rank One Editing for Text-to-Image Personalization. ACM SIGGRAPH 2023 Conference Proceedings (2023). https:\/\/api.semanticscholar.org\/CorpusID:258436985"},{"key":"e_1_3_2_2_36_1","unstructured":"Vaibhav Vavilala and David Forsyth. 2023. Applying a Color Palette with Local Control using Diffusion Models. arxiv:2307.02698\u00a0[cs.CV]"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"e_1_3_2_2_40_1","volume-title":"Pretraining is all you need for image-to-image translation. arXiv preprint arXiv:2205.12952","author":"Wang Tengfei","year":"2022","unstructured":"Tengfei Wang, Ting Zhang, Bo Zhang, Hao Ouyang, Dong Chen, Qifeng Chen, and Fang Wen. 2022. Pretraining is all you need for image-to-image translation. arXiv preprint arXiv:2205.12952 (2022)."},{"key":"e_1_3_2_2_41_1","unstructured":"Shih-En Wei Varun Ramakrishna Takeo Kanade and Yaser Sheikh. 2016. Convolutional pose machines. In CVPR."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"e_1_3_2_2_43_1","volume-title":"Diffusion-based scene graph to image generation with masked contrastive pre-training. arXiv preprint arXiv:2211.11138","author":"Yang Ling","year":"2022","unstructured":"Ling Yang, Zhilin Huang, Yang Song, Shenda Hong, Guohao Li, Wentao Zhang, Bin Cui, Bernard Ghanem, and Ming-Hsuan Yang. 2022. Diffusion-based scene graph to image generation with masked contrastive pre-training. arXiv preprint arXiv:2211.11138 (2022)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592103"}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657525","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:50Z","timestamp":1750291550000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":46,"alternative-id":["10.1145\/3641519.3657525","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657525","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}