{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:37:31Z","timestamp":1783967851992,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763943","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:27:29Z","timestamp":1765211249000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0170-3363","authenticated-orcid":false,"given":"Xuancheng","family":"Jin","sequence":"first","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China and Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-7635","authenticated-orcid":false,"given":"Rengan","family":"Xie","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4389-7631","authenticated-orcid":false,"given":"Wenting","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4267-0347","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2662-0334","authenticated-orcid":false,"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3296-7999","authenticated-orcid":false,"given":"Yuchi","family":"Huo","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China and Zhejiang Lab, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"crossref","unstructured":"Sherwin Bahmani Jeong\u00a0Joon Park Despoina Paschalidou Xingguang Yan Gordon Wetzstein Leonidas Guibas and Andrea Tagliasacchi. 2023. CC3D: Layout-Conditioned Generation of Compositional 3D Scenes. arxiv:https:\/\/arXiv.org\/abs\/2303.12074\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2303.12074","DOI":"10.1109\/ICCV51070.2023.00659"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","unstructured":"Maciej Bala Yin Cui Yifan Ding Yunhao Ge Zekun Hao Jon Hasselgren Jacob\u00a0Samuel Huffman Jingyi Jin J.\u00a0P. Lewis Zhaoshuo Li Chen-Hsuan Lin Yen-Chen Lin Tsung-Yi Lin Ming-Yu Liu Alice Luo Qianli Ma Jacob Munkberg Stella Shi Fangyin Wei Donglai Xiang Jiashu Xu Xiaohui Zeng and Qinsheng Zhang. 2024. Edify 3D: Scalable High-Quality 3D Asset Generation. CoRR abs\/2411.07135 (2024). https:\/\/doi.org\/10.48550\/arXiv.2411.07135","DOI":"10.48550\/arXiv.2411.07135"},{"key":"e_1_3_3_2_5_1","unstructured":"Roi Bar-On Dana Cohen-Bar and Daniel Cohen-Or. 2025. EditP23: 3D Editing via Propagation of Image Prompts to Multi-View. arxiv:https:\/\/arXiv.org\/abs\/2506.20652\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2506.20652"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Yang Chen Yingwei Pan Yehao Li Ting Yao and Tao Mei. 2023b. Control3D: Towards Controllable Text-to-3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2311.05461\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2311.05461","DOI":"10.1145\/3581783.3612489"},{"key":"e_1_3_3_2_9_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Cheng Xinhua","year":"2024","unstructured":"Xinhua Cheng, Tianyu Yang, Jianan Wang, Yu Li, Lei Zhang, Jian Zhang, and Li Yuan. 2024. Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=O072Rc8uUy"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"e_1_3_3_2_11_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Darcet Timoth\u00e9e","year":"2024","unstructured":"Timoth\u00e9e Darcet, Maxime Oquab, Julien Mairal, and Piotr Bojanowski. 2024. Vision Transformers Need Registers. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2dnO3LLiJ1"},{"key":"e_1_3_3_2_12_1","series-title":"(NIPS \u201921)","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alex Nichol. 2021. Diffusion models beat GANs on image synthesis. In Proceedings of the 35th International Conference on Neural Information Processing Systems(NIPS \u201921). Curran Associates Inc., Red Hook, NY, USA, Article 672, 15\u00a0pages."},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657425"},{"key":"e_1_3_3_2_14_1","volume-title":"Advances In Neural Information Processing Systems","author":"Gao Jun","year":"2022","unstructured":"Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, and Sanja Fidler. 2022. GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images. In Advances In Neural Information Processing Systems."},{"key":"e_1_3_3_2_15_1","volume-title":"ICCV","author":"Gao William","year":"2025","unstructured":"William Gao, Dilin Wang, Yuchen Fan, Alja\u017e Bo\u017ei\u010d, Tuur Stuyck, Zhengqin Li, Zhao Dong, Rakesh Ranjan, and Nikolaos Sarafianos. 2025. 3D Mesh Editing using Masked LRMs. In ICCV."},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"crossref","unstructured":"Dimitrios Gerogiannis Foivos\u00a0Paraperas Papantoniou Rolandos\u00a0Alexandros Potamias Alexandros Lattas and Stefanos Zafeiriou. 2025. Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.05379 (2025).","DOI":"10.1109\/CVPR52734.2025.01006"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2020. Generative adversarial networks. 63 11 (Oct. 2020) 139\u2013144. 10.1145\/3422622","DOI":"10.1145\/3422622"},{"key":"e_1_3_3_2_18_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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.01626 (2022)."},{"key":"e_1_3_3_2_19_1","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 574, 12\u00a0pages."},{"key":"e_1_3_3_2_20_1","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arxiv:https:\/\/arXiv.org\/abs\/2207.12598\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2207.12598"},{"key":"e_1_3_3_2_21_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hong Yicong","year":"2024","unstructured":"Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2024. LRM: Large Reconstruction Model for Single Image to 3D. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sllU8vvsFF"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Xin Huang Ruizhi Shao Qi Zhang Hongwen Zhang Ying Feng Yebin Liu and Qing Wang. 2024. Humannorm: Learning normal diffusion model for high-quality and realistic 3d human generation.","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"e_1_3_3_2_23_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ignatyev Savva\u00a0Victorovich","year":"2025","unstructured":"Savva\u00a0Victorovich Ignatyev, Nina Konovalova, Daniil Selikhanovych, Oleg Voynov, Nikolay Patakin, Ilya Olkov, Dmitry Senushkin, Alexey Artemov, Anton Konushin, Alexander Filippov, Peter Wonka, and Evgeny Burnaev. 2025. A3D: Does Diffusion Dream about 3D Alignment?. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=QQCIfkhGIq"},{"key":"e_1_3_3_2_24_1","unstructured":"Heewoo Jun and Alex Nichol. 2023. Shap-E: Generating Conditional 3D Implicit Functions. arxiv:https:\/\/arXiv.org\/abs\/2305.02463\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2305.02463"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","unstructured":"Tero Karras Samuli Laine and Timo Aila. 2021. A Style-Based Generator Architecture for Generative Adversarial Networks. IEEE Trans. Pattern Anal. Mach. Intell. 43 12 (Dec. 2021) 4217\u20134228. 10.1109\/TPAMI.2020.2970919","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"e_1_3_3_2_27_1","unstructured":"Yuhan Li Yishun Dou Yue Shi Yu Lei Xuanhong Chen Yi Zhang Peng Zhou and Bingbing Ni. 2023a. FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly. arxiv:https:\/\/arXiv.org\/abs\/2308.10608\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2308.10608"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_2_29_1","first-page":"128911","volume-title":"Advances in Neural Information Processing Systems","author":"Lin Kuan Heng","year":"2024","unstructured":"Kuan Heng Lin, Sicheng Mo, Ben Klingher, Fangzhou Mu, and Bolei Zhou. 2024. Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance. In Advances in Neural Information Processing Systems , Vol.\u00a037. 128911\u2013128939."},{"key":"e_1_3_3_2_30_1","unstructured":"Yuchen Lin Chenguo Lin Panwang Pan Honglei Yan Yiqiang Feng Yadong Mu and Katerina Fragkiadaki. 2025. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers. arXiv:https:\/\/arXiv.org\/abs\/2506.05573https:\/\/arxiv.org\/abs\/2506.05573"},{"key":"e_1_3_3_2_31_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_32_1","unstructured":"Xingchao Liu Chengyue Gong and Qiang Liu. 2022. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow. arxiv:https:\/\/arXiv.org\/abs\/2209.03003\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2209.03003"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Xiaoxiao Long Yuan-Chen Guo Cheng Lin Yuan Liu Zhiyang Dou Lingjie Liu Yuexin Ma Song-Hai Zhang Marc Habermann Christian Theobalt et\u00a0al. 2023. Wonder3D: Single Image to 3D using Cross-Domain Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.15008 (2023).","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_3_2_34_1","unstructured":"Rui Mao Guanyi Chen Xulang Zhang Frank Guerin and Erik Cambria. 2024. GPTEval: A Survey on Assessments of ChatGPT and GPT-4. arxiv:https:\/\/arXiv.org\/abs\/2308.12488\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2308.12488"},{"key":"e_1_3_3_2_35_1","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:https:\/\/arXiv.org\/abs\/2211.07600\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.07600"},{"key":"e_1_3_3_2_36_1","unstructured":"Alex Nichol Heewoo Jun Prafulla Dhariwal Pamela Mishkin and Mark Chen. 2022. Point-E: A System for Generating 3D Point Clouds from Complex Prompts. arxiv:https:\/\/arXiv.org\/abs\/2212.08751\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2212.08751"},{"key":"e_1_3_3_2_37_1","unstructured":"OpenAI. 2024. GPT-4o System Card. arxiv:https:\/\/arXiv.org\/abs\/2410.21276\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_3_2_38_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby Mahmoud Assran Nicolas Ballas Wojciech Galuba Russell Howes Po-Yao Huang Shang-Wen Li Ishan Misra Michael Rabbat Vasu Sharma Gabriel Synnaeve Hu Xu Herv\u00e9 Jegou Julien Mairal Patrick Labatut Armand Joulin and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features without Supervision. arxiv:https:\/\/arXiv.org\/abs\/2304.07193\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2304.07193"},{"key":"e_1_3_3_2_39_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T. Barron and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2209.14988\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2209.14988"},{"key":"e_1_3_3_2_40_1","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. arxiv:https:\/\/arXiv.org\/abs\/2103.00020\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Amit Raj Srinivas Kaza Ben Poole Michael Niemeyer Ben Mildenhall Nataniel Ruiz Shiran Zada Kfir Aberman Michael Rubenstein Jonathan Barron Yuanzhen Li and Varun Jampani. 2023. DreamBooth3D: Subject-Driven Text-to-3D Generation. ICCV (2023).","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"e_1_3_3_2_42_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arxiv:https:\/\/arXiv.org\/abs\/2204.06125\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2204.06125"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_44_1","series-title":"(NIPS \u201922)","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Lit, Jay Whang, Emily Denton, Seyed Kamyar\u00a0Seyed Ghasemipour, Burcu\u00a0Karagol Ayan, S.\u00a0Sara Mahdavi, Raphael Gontijo-Lopes, Tim Salimans, Jonathan Ho, David\u00a0J Fleet, and Mohammad Norouzi. 2022. Photorealistic text-to-image diffusion models with deep language understanding. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201922). Curran Associates Inc., Red Hook, NY, USA, Article 2643, 16\u00a0pages."},{"key":"e_1_3_3_2_45_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. https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Jiaxiang Tang Zhaoxi Chen Xiaokang Chen Tengfei Wang Gang Zeng and Ziwei Liu. 2024. LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation. arxiv:https:\/\/arXiv.org\/abs\/2402.05054\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2402.05054","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"e_1_3_3_2_47_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","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 Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ppJuFSOAnM"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"crossref","unstructured":"Jianfeng Xiang Zelong Lv Sicheng Xu Yu Deng Ruicheng Wang Bowen Zhang Dong Chen Xin Tong and Jiaolong Yang. 2025. Structured 3D Latents for Scalable and Versatile 3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2412.01506\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.01506","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_2_49_1","unstructured":"Rengan Xie Wenting Zheng Kai Huang Yizheng Chen Qi Wang Qi Ye Wei Chen and Yuchi Huo. 2024. LDM: Large Tensorial SDF Model for Textured Mesh Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.14580 (2024)."},{"key":"e_1_3_3_2_50_1","unstructured":"Jiale Xu Weihao Cheng Yiming Gao Xintao Wang Shenghua Gao and Ying Shan. 2024a. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models. arxiv:https:\/\/arXiv.org\/abs\/2404.07191\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2404.07191"},{"key":"e_1_3_3_2_51_1","first-page":"15903","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. ImageReward: learning and evaluating human preferences for text-to-image generation. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 15903\u201315935."},{"key":"e_1_3_3_2_52_1","unstructured":"Yuanyou Xu Zongxin Yang and Yi Yang. 2024b. SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons. https:\/\/openreview.net\/forum?id=6r1nbspMUl"},{"key":"e_1_3_3_2_53_1","unstructured":"Chenglin Yang Celong Liu Xueqing Deng Dongwon Kim Xing Mei Xiaohui Shen and Liang-Chieh Chen. 2024. 1.58-bit FLUX. arxiv:https:\/\/arXiv.org\/abs\/2412.18653\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.18653"},{"key":"e_1_3_3_2_54_1","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2308.06721\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2308.06721"},{"key":"e_1_3_3_2_55_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yu Xin","year":"2024","unstructured":"Xin Yu, Yuan-Chen Guo, Yangguang Li, Ding Liang, Song-Hai Zhang, and XIAOJUAN QI. 2024. Text-to-3D with Classifier Score Distillation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ktG8Tun1Cy"},{"key":"e_1_3_3_2_56_1","unstructured":"Bohan Zeng Shanglin Li Yutang Feng Ling Yang Hong Li Sicheng Gao Jiaming Liu Conghui He Wentao Zhang Jianzhuang Liu Baochang Zhang and Shuicheng Yan. 2023. Ipdreamer: Appearance-controllable 3d object generation with image prompts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.05375 (2023)."},{"key":"e_1_3_3_2_57_1","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. [n. d.]. Adding Conditional Control to Text-to-Image Diffusion Models."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","unstructured":"Longwen Zhang Ziyu Wang Qixuan Zhang Qiwei Qiu Anqi Pang Haoran Jiang Wei Yang Lan Xu and Jingyi Yu. 2024. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets. ACM Trans. Graph. 43 4 Article 120 (July 2024) 20\u00a0pages. 10.1145\/3658146","DOI":"10.1145\/3658146"}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:27:43Z","timestamp":1765250863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":57,"alternative-id":["10.1145\/3757377.3763943","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763943","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}