{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T11:33:02Z","timestamp":1775043182978,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ISF","award":["2492\/20"],"award-info":[{"award-number":["2492\/20"]}]},{"name":"Packard Fellowship"},{"name":"Sony Corporation"},{"name":"Cisco Research"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687611","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Consolidating Attention Features for Multi-view Image Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7757-6137","authenticated-orcid":false,"given":"Or","family":"Patashnik","sequence":"first","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4875-965X","authenticated-orcid":false,"given":"Rinon","family":"Gal","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel and NVIDIA Research, Tel Aviv, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6777-7445","authenticated-orcid":false,"given":"Daniel","family":"Cohen-Or","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8504-3410","authenticated-orcid":false,"given":"Jun-Yan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7086-8572","authenticated-orcid":false,"given":"Fernando","family":"De La Torre","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Yuval Alaluf Daniel Garibi Or Patashnik Hadar Averbuch-Elor and Daniel Cohen-Or. 2023. Cross-Image Attention for Zero-Shot Appearance Transfer. arxiv:https:\/\/arXiv.org\/abs\/2311.03335\u00a0[cs.CV]","DOI":"10.1145\/3641519.3657423"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_34"},{"key":"e_1_3_3_2_4_1","unstructured":"Shariq\u00a0Farooq Bhat Niloy\u00a0J. Mitra and Peter Wonka. 2023. LooseControl: Lifting ControlNet for Generalized Depth Conditioning. arxiv:https:\/\/arXiv.org\/abs\/2312.03079\u00a0[cs.CV]"},{"key":"e_1_3_3_2_5_1","volume-title":"International Conference on Learning Representations","author":"Bi\u0144kowski Miko\u0142aj","year":"2018","unstructured":"Miko\u0142aj Bi\u0144kowski, Danica\u00a0J Sutherland, Michael Arbel, and Arthur Gretton. 2018. Demystifying MMD GANs. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_6_1","unstructured":"Manuel Brack Felix Friedrich Dominik Hintersdorf Lukas Struppek Patrick Schramowski and Kristian Kersting. 2023. SEGA: Instructing Text-to-Image Models using Semantic Guidance. arxiv:https:\/\/arXiv.org\/abs\/2301.12247\u00a0[cs.CV]"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Tim Brooks Aleksander Holynski and Alexei\u00a0A Efros. 2022. InstructPix2Pix: Learning to Follow Image Editing Instructions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.09800 (2022).","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_8_1","unstructured":"Mingdeng Cao Xintao Wang Zhongang Qi Ying Shan Xiaohu Qie and Yinqiang Zheng. 2023. MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing. arxiv:https:\/\/arXiv.org\/abs\/2304.08465\u00a0[cs.CV]"},{"key":"e_1_3_3_2_9_1","volume-title":"arXiv","author":"Chan Eric\u00a0R.","year":"2021","unstructured":"Eric\u00a0R. Chan, Connor\u00a0Z. Lin, Matthew\u00a0A. Chan, Koki Nagano, Boxiao Pan, Shalini\u00a0De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, and Gordon Wetzstein. 2021a. Efficient Geometry-aware 3D Generative Adversarial Networks. In arXiv."},{"key":"e_1_3_3_2_10_1","volume-title":"arXiv","author":"Chan Eric\u00a0R.","year":"2021","unstructured":"Eric\u00a0R. Chan, Connor\u00a0Z. Lin, Matthew\u00a0A. Chan, Koki Nagano, Boxiao Pan, Shalini\u00a0De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, and Gordon Wetzstein. 2021b. Efficient Geometry-aware 3D Generative Adversarial Networks. In arXiv."},{"key":"e_1_3_3_2_11_1","volume-title":"arXiv","author":"Chan Eric\u00a0R.","year":"2023","unstructured":"Eric\u00a0R. Chan, Koki Nagano, Matthew\u00a0A. Chan, Alexander\u00a0W. Bergman, Jeong\u00a0Joon Park, Axel Levy, Miika Aittala, Shalini\u00a0De Mello, Tero Karras, and Gordon Wetzstein. 2023. GeNVS: Generative Novel View Synthesis with 3D-Aware Diffusion Models. In arXiv."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Hila Chefer Yuval Alaluf Yael Vinker Lior Wolf and Daniel Cohen-Or. 2023. Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2301.13826\u00a0[cs.CV]","DOI":"10.1145\/3592116"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01197"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"e_1_3_3_2_16_1","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_3_2_17_1","unstructured":"Dave Epstein Allan Jabri Ben Poole Alexei\u00a0A. Efros and Aleksander Holynski. 2023. Diffusion Self-Guidance for Controllable Image Generation. (2023)."},{"key":"e_1_3_3_2_18_1","unstructured":"Zhiwen Fan Yifan Jiang Peihao Wang Xinyu Gong Dejia Xu and Zhangyang Wang. 2022. Unified Implicit Neural Stylization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.01943 (2022)."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"e_1_3_3_2_20_1","unstructured":"Michal Geyer Omer Bar-Tal Shai Bagon and Tali Dekel. 2023. TokenFlow: Consistent Diffusion Features for Consistent Video Editing. arXiv preprint arxiv:https:\/\/arXiv.org\/abs\/2307.10373 (2023)."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"e_1_3_3_2_23_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. (2022)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Amir Hertz Andrey Voynov Shlomi Fruchter and Daniel Cohen-Or. 2023b. Style Aligned Image Generation via Shared Attention. (2023).","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00482"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01780"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Inbar Huberman-Spiegelglas Vladimir Kulikov and Tomer Michaeli. 2023. An Edit Friendly DDPM Noise Space: Inversion and Manipulations. arxiv:https:\/\/arXiv.org\/abs\/2304.06140\u00a0[cs.CV]","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"e_1_3_3_2_28_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Katzir Oren","year":"2024","unstructured":"Oren Katzir, Or Patashnik, Daniel Cohen-Or, and Dani Lischinski. 2024. Noise-free Score Distillation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=dlIMcmlAdk"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics 42 4 (July 2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Umar Khalid Hasan Iqbal Nazmul Karim Jing Hua and Chen Chen. 2023. LatentEditor: Text Driven Local Editing of 3D Scenes. arxiv:https:\/\/arXiv.org\/abs\/2312.09313\u00a0[cs.CV]","DOI":"10.1007\/978-3-031-73039-9_21"},{"key":"e_1_3_3_2_33_1","unstructured":"Subin Kim Kyungmin Lee June\u00a0Suk Choi Jongheon Jeong Kihyuk Sohn and Jinwoo Shin. 2023. Collaborative Score Distillation for Consistent Visual Synthesis. arxiv:https:\/\/arXiv.org\/abs\/2307.04787\u00a0[cs.CV]"},{"key":"e_1_3_3_2_34_1","volume-title":"Advances in Neural Information Processing Systems","author":"Kobayashi Sosuke","year":"2022","unstructured":"Sosuke Kobayashi, Eiichi Matsumoto, and Vincent Sitzmann. 2022. Decomposing NeRF for Editing via Feature Field Distillation. In Advances in Neural Information Processing Systems , Vol.\u00a035. https:\/\/arxiv.org\/pdf\/2205.15585.pdf"},{"key":"e_1_3_3_2_35_1","unstructured":"Juil Koo Chanho Park and Minhyuk Sung. 2023. Posterior Distillation Sampling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.13831 (2023)."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_12"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00323"},{"key":"e_1_3_3_2_38_1","unstructured":"Senmao Li Taihang Hu Fahad\u00a0Shahbaz Khan Linxuan Li Shiqi Yang Yaxing Wang Ming-Ming Cheng and Jian Yang. 2023. Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2312.09608\u00a0[cs.CV]"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_2_40_1","unstructured":"Ruoshi Liu Rundi Wu Basile\u00a0Van Hoorick Pavel Tokmakov Sergey Zakharov and Carl Vondrick. 2023. Zero-1-to-3: Zero-shot One Image to 3D Object. arxiv:https:\/\/arXiv.org\/abs\/2303.11328\u00a0[cs.CV]"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00572"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Nelson Max. 1995. Optical models for direct volume rendering. IEEE Transactions on Visualization and Computer Graphics 1 2 (1995) 99\u2013108.","DOI":"10.1109\/2945.468400"},{"key":"e_1_3_3_2_43_1","volume-title":"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 International Conference on Learning Representations."},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Gal Metzer Elad Richardson Or Patashnik Raja Giryes and Daniel Cohen-Or. 2022. Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.07600 (2022).","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","unstructured":"Thomas M\u00fcller Alex Evans Christoph Schied and Alexander Keller. 2022. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. ACM Trans. Graph. 41 4 Article 102 (July 2022) 15\u00a0pages. 10.1145\/3528223.3530127https:\/\/dl.acm.org\/doi\/10.1145\/3528223.3530127","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00768"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","unstructured":"Thu Nguyen-Phuoc Feng Liu and Lei Xiao. 2022. SNeRF: stylized neural implicit representations for 3D scenes. ACM Transactions on Graphics 41 4 (July 2022) 1\u201311. 10.1145\/3528223.3530107https:\/\/dl.acm.org\/doi\/10.1145\/3528223.3530107","DOI":"10.1145\/3528223.3530107"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"e_1_3_3_2_50_1","first-page":"13503","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Or-El Roy","year":"2022","unstructured":"Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong\u00a0Joon Park, and Ira Kemelmacher-Shlizerman. 2022. StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13503\u201313513."},{"key":"e_1_3_3_2_51_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Park JangHo","year":"2024","unstructured":"JangHo Park, Gihyun Kwon, and Jong\u00a0Chul Ye. 2024. ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=9DvDRTTdlu"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"e_1_3_3_2_54_1","volume-title":"Thirty-Sixth Conference on Neural Information Processing Systems","author":"Peng Yicong","year":"2022","unstructured":"Yicong Peng, Yichao Yan, Shenqi Liu, Yuhao Cheng, Shanyan Guan, Bowen Pan, Guangtao Zhai, and Xiaokang Yang. 2022. CageNeRF: Cage-based Neural Radiance Fields for Genrenlized 3D Deformation and Animation. In Thirty-Sixth Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_2_55_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T. Barron and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. arXiv (2022)."},{"key":"e_1_3_3_2_56_1","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2112.10752\u00a0[cs.CV]"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_2_58_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shi Yichun","year":"2024","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FUgrjq2pbB"},{"key":"e_1_3_3_2_59_1","unstructured":"Ka\u00a0Chun Shum Jaeyeon Kim Binh-Son Hua Duc\u00a0Thanh Nguyen and Sai-Kit Yeung. 2023. Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates. arxiv:https:\/\/arXiv.org\/abs\/2309.11281\u00a0[cs.CV]"},{"key":"e_1_3_3_2_60_1","volume-title":"International Conference on Learning Representations","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_61_1","unstructured":"Liangchen Song Liangliang Cao Jiatao Gu Yifan Jiang Junsong Yuan and Hao Tang. 2023. Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.08563 (2023)."},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01609"},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_3_2_66_1","unstructured":"Can Wang Menglei Chai Mingming He Dongdong Chen and Jing Liao. 2021a. CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.05139 (2021)."},{"key":"e_1_3_3_2_67_1","unstructured":"Can Wang Ruixiang Jiang Menglei Chai Mingming He Dongdong Chen and Jing Liao. 2022. NeRF-Art: Text-Driven Neural Radiance Fields Stylization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.08070 (2022)."},{"key":"e_1_3_3_2_68_1","unstructured":"Peng Wang Lingjie Liu Yuan Liu Christian Theobalt Taku Komura and Wenping Wang. 2021b. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.10689 (2021)."},{"key":"e_1_3_3_2_69_1","unstructured":"Peng Wang and Yichun Shi. 2023. ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.02201 (2023)."},{"key":"e_1_3_3_2_70_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_71_1","unstructured":"Daniel Watson William Chan Ricardo Martin-Brualla Jonathan Ho Andrea Tagliasacchi and Mohammad Norouzi. 2022. Novel View Synthesis with Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2210.04628\u00a0[cs.CV]"},{"key":"e_1_3_3_2_72_1","volume-title":"arXiv","author":"Weber Ethan","year":"2023","unstructured":"Ethan Weber, Aleksander Holynski, Varun Jampani, Saurabh Saxena, Noah Snavely, Abhishek Kar, and Angjoo Kanazawa. 2023. NeRFiller: Completing Scenes via Generative 3D Inpainting. In arXiv."},{"key":"e_1_3_3_2_73_1","unstructured":"Rundi Wu Ben Mildenhall Philipp Henzler Keunhong Park Ruiqi Gao Daniel Watson Pratul\u00a0P. Srinivasan Dor Verbin Jonathan\u00a0T. Barron Ben Poole and Aleksander Holynski. 2023. ReconFusion: 3D Reconstruction with Diffusion Priors. arXiv (2023)."},{"key":"e_1_3_3_2_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_10"},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"e_1_3_3_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01781"},{"key":"e_1_3_3_2_77_1","doi-asserted-by":"crossref","unstructured":"Yu-Jie Yuan Yang-Tian Sun Yu-Kun Lai Yuewen Ma Rongfei Jia Leif Kobbelt and Lin Gao. 2023. Interactive NeRF Geometry Editing with Shape Priors. (2023).","DOI":"10.1109\/TPAMI.2023.3315068"},{"key":"e_1_3_3_2_78_1","doi-asserted-by":"crossref","unstructured":"Kai Zhang Nick Kolkin Sai Bi Fujun Luan Zexiang Xu Eli Shechtman and Noah Snavely. 2022. ARF: Artistic Radiance Fields.","DOI":"10.1007\/978-3-031-19821-2_41"},{"key":"e_1_3_3_2_79_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_80_1","unstructured":"Junzhe Zhu and Peiye Zhuang. 2023. HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance. arxiv:https:\/\/arXiv.org\/abs\/2305.18766\u00a0[cs.CV]"},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"crossref","unstructured":"Jingyu Zhuang Di Kang Yan-Pei Cao Guanbin Li Liang Lin and Ying Shan. 2024. TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts. arxiv:https:\/\/arXiv.org\/abs\/2401.14828\u00a0[cs.CV]","DOI":"10.1145\/3658205"},{"key":"e_1_3_3_2_82_1","doi-asserted-by":"crossref","unstructured":"Jingyu Zhuang Chen Wang Lingjie Liu Liang Lin and Guanbin Li. 2023. DreamEditor: Text-Driven 3D Scene Editing with Neural Fields. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.13455 (2023).","DOI":"10.1145\/3610548.3618190"}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Conference Papers","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687611","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:26Z","timestamp":1750294706000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":81,"alternative-id":["10.1145\/3680528.3687611","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687611","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}