{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:04:47Z","timestamp":1784228687334,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811141","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0079-0046","authenticated-orcid":false,"given":"Etai","family":"Sella","sequence":"first","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6834-4139","authenticated-orcid":false,"given":"Hao","family":"Phung","sequence":"additional","affiliation":[{"name":"Cornell Tech, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5492-8334","authenticated-orcid":false,"given":"Nitay","family":"Amiel","sequence":"additional","affiliation":[{"name":"Technion - Israel Institute of Technology, Haifa, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6700-7379","authenticated-orcid":false,"given":"Or","family":"Litany","sequence":"additional","affiliation":[{"name":"Technion - Israel Institute of Technology, Haifa, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7757-6137","authenticated-orcid":false,"given":"Or","family":"Patashnik","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3476-0940","authenticated-orcid":false,"given":"Hadar","family":"Averbuch-Elor","sequence":"additional","affiliation":[{"name":"Cornell Tech, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","first-page":"6","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"2","author":"Achlioptas Panos","year":"2022","unstructured":"Panos Achlioptas, Ian Huang, Minhyuk Sung, Sergey Tulyakov, and Leonidas Guibas. 2022. ChangeIt3D: Languageassisted 3d shape edits and deformations. In Conference on Computer Vision and Pattern Recognition (CVPR) , Vol.\u00a02. 6."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01220"},{"key":"e_1_3_3_2_4_1","first-page":"247","volume-title":"European Conference on Computer Vision","author":"Avetisyan Armen","year":"2024","unstructured":"Armen Avetisyan, Christopher Xie, Henry Howard-Jenkins, Tsun-Yi Yang, Samir Aroudj, Suvam Patra, Fuyang Zhang, Duncan Frost, Luke Holland, Campbell Orme, et\u00a0al. 2024. Scenescript: Reconstructing scenes with an autoregressive structured language model. In European Conference on Computer Vision. Springer, 247\u2013263."},{"key":"e_1_3_3_2_5_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et\u00a0al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.13923 (2025)."},{"key":"e_1_3_3_2_6_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2506.20652 (2025)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Amir Barda Matheus Gadelha Vladimir\u00a0G. Kim Noam Aigerman Amit\u00a0H. Bermano and Thibault Groueix. 2025. Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects.","DOI":"10.1109\/CVPR52734.2025.01517"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Alan\u00a0H Barr. 1981. Superquadrics and angle-preserving transformations. IEEE Computer graphics and Applications 1 01 (1981) 11\u201323.","DOI":"10.1109\/MCG.1981.1673799"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Bahri\u00a0Batuhan Bilecen Yigit Yalin Ning Yu and Aysegul Dundar. 2024. Reference-Based 3D-Aware Image Editing with Triplanes. arxiv:https:\/\/arXiv.org\/abs\/2404.03632\u00a0[cs.CV]","DOI":"10.1109\/CVPR52734.2025.00554"},{"key":"e_1_3_3_2_10_1","unstructured":"Cheng-Kang\u00a0Ted Chao and Yotam Gingold. 2023. Text-guided image-and-shape editing and generation: A short survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.09244 (2023)."},{"key":"e_1_3_3_2_11_1","first-page":"74","volume-title":"European Conference on Computer Vision","author":"Chen Minghao","year":"2024","unstructured":"Minghao Chen, Iro Laina, and Andrea Vedaldi. 2024a. Dge: Direct gaussian 3d editing by consistent multi-view editing. In European Conference on Computer Vision. Springer, 74\u201392."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02498"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Yongwei Chen Rui Chen Jiabao Lei Yabin Zhang and Kui Jia. 2022. Tango: Text-driven photorealistic and robust 3d stylization via lighting decomposition. Advances in Neural Information Processing Systems 35 (2022) 30923\u201330936.","DOI":"10.52202\/068431-2242"},{"key":"e_1_3_3_2_15_1","unstructured":"SeungJeh Chung JooHyun Park and HyeongYeop Kang. 2024. 3dstyleglip: Part-tailored text-guided 3d neural stylization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02634 (2024)."},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01999"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00068"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01305"},{"key":"e_1_3_3_2_19_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Fedele Elisabetta","year":"2026","unstructured":"Elisabetta Fedele, Francis Engelmann, Ian Huang, Or Litany, Marc Pollefeys, and Leonidas Guibas. 2026. SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Elisabetta Fedele Boyang Sun Leonidas Guibas Marc Pollefeys and Francis Engelmann. 2025. Superdec: 3d scene decomposition with superquadric primitives. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.00992 (2025).","DOI":"10.1109\/ICCV51701.2025.02283"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591552"},{"key":"e_1_3_3_2_22_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Gilo Daniel","year":"2026","unstructured":"Daniel Gilo and Or Litany. 2026. InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_23_1","unstructured":"Google DeepMind. 2025. Introducing Gemini 2.5 Flash Image our state-of-the-art image generation and editing model. https:\/\/developers.googleblog.com\/en\/introducing-gemini-2-5-flash-image\/. Accessed: 2025-11-13."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Shrisudhan Govindarajan Daniel Rebain Kwang\u00a0Moo Yi and Andrea Tagliasacchi. 2025. Radiant foam: Real-time differentiable ray tracing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01157 (2025).","DOI":"10.1109\/ICCV51701.2025.00394"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00765"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01990"},{"key":"e_1_3_3_2_28_1","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 30 (2017)."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657412"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Ian Huang Panos Achlioptas Tianyi Zhang Sergey Tulyakov Minhyuk Sung and Leonidas Guibas. 2022. LADIS: Language disentanglement for 3D shape editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.05011 (2022).","DOI":"10.18653\/v1\/2022.findings-emnlp.404"},{"key":"e_1_3_3_2_31_1","unstructured":"Heewoo Jun and Alex Nichol. 2023. Shap-e: Generating conditional 3d implicit functions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.02463 (2023)."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Kunal Kathare Ankit Dhiman K\u00a0Vikas Gowda Siddharth Aravindan Shubham Monga Basavaraja\u00a0Shanthappa Vandrotti and Lokesh\u00a0R Boregowda. 2025. Instructive3D: Editing Large Reconstruction Models with Text Instructions. arxiv:https:\/\/arXiv.org\/abs\/2501.04374\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2501.04374","DOI":"10.1109\/WACV61041.2025.00321"},{"key":"e_1_3_3_2_33_1","unstructured":"Black\u00a0Forest Labs Stephen Batifol Andreas Blattmann Frederic Boesel Saksham Consul Cyril Diagne Tim Dockhorn Jack English Zion English Patrick Esser Sumith Kulal Kyle Lacey Yam Levi Cheng Li Dominik Lorenz Jonas M\u00fcller Dustin Podell Robin Rombach Harry Saini Axel Sauer and Luke Smith. 2025. FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space. arxiv:https:\/\/arXiv.org\/abs\/2506.15742\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2506.15742"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Lin Li Zehuan Huang Haoran Feng Gengxiong Zhuang Rui Chen Chunchao Guo and Lu Sheng. 2025. Voxhammer: Training-free precise and coherent 3d editing in native 3d space. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.19247 (2025).","DOI":"10.1109\/3DV69130.2026.00126"},{"key":"e_1_3_3_2_35_1","first-page":"366","volume-title":"European Conference on Computer Vision","author":"Lin Zhiqiu","year":"2024","unstructured":"Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide Xia, Graham Neubig, Pengchuan Zhang, and Deva Ramanan. 2024. Evaluating text-to-visual generation with image-to-text generation. In European Conference on Computer Vision. Springer, 366\u2013384."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Zhengzhe Liu Jingyu Hu Ka-Hei Hui Xiaojuan Qi Daniel Cohen-Or and Chi-Wing Fu. 2023. EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation. ACM Transactions on Graphics (TOG) 42 6 (2023) 1\u201312.","DOI":"10.1145\/3618312"},{"key":"e_1_3_3_2_37_1","unstructured":"Sining Lu Guan Chen Nam\u00a0Anh Dinh Itai Lang Ari Holtzman and Rana Hanocka. 2025. Ll3m: Large language 3d modelers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.08228 (2025)."},{"key":"e_1_3_3_2_38_1","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Man Brandon","year":"2025","unstructured":"Brandon Man, Ghadi Nehme, Md\u00a0Ferdous Alam, and Faez Ahmed. 2025. VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video. In The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"crossref","unstructured":"Hengyu Meng Duotun Wang Zhijing Shao Ligang Liu and Zeyu Wang. 2025. Text2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D Sculpting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.20045 (2025).","DOI":"10.1109\/ICCV51701.2025.01568"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"e_1_3_3_2_41_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2212.08751 (2022)."},{"key":"e_1_3_3_2_42_1","unstructured":"Francesco Palandra Andrea Sanchietti Daniele Baieri and Emanuele Rodola. 2024. Gsedit: Efficient text-guided editing of 3d objects via gaussian splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.05154 (2024)."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00322"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01059"},{"key":"e_1_3_3_2_45_1","first-page":"695","volume-title":"AAAI","author":"Pentland Alex","year":"1986","unstructured":"Alex Pentland. 1986. Parts: Structured Descriptions of Shape.. In AAAI. 695\u2013701."},{"key":"e_1_3_3_2_46_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988 (2022)."},{"key":"e_1_3_3_2_47_1","first-page":"652","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi Charles\u00a0R","year":"2017","unstructured":"Charles\u00a0R Qi, Hao Su, Kaichun Mo, and Leonidas\u00a0J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 652\u2013660."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01777"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657461"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00396"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00119"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.160"},{"key":"e_1_3_3_2_55_1","unstructured":"Zhengyi Wang Jonathan Lorraine Yikai Wang Hang Su Jun Zhu Sanja Fidler and Xiaohui Zeng. 2024. Llama-mesh: Unifying 3d mesh generation with language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.09595 (2024)."},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01959"},{"key":"e_1_3_3_2_57_1","unstructured":"Ruihao Xia Yang Tang and Pan Zhou. 2025. Towards Scalable and Consistent 3D Editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.02994 (2025)."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02479"},{"key":"e_1_3_3_2_60_1","unstructured":"Jingwen Ye Yuze He Yanning Zhou Yiqin Zhu Kaiwen Xiao Yong-Jin Liu Wei Yang and Xiao Han. 2025a. PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer. arxiv:https:\/\/arXiv.org\/abs\/2505.04622\u00a0[cs.GR]"},{"key":"e_1_3_3_2_61_1","unstructured":"Junliang Ye Shenghao Xie Ruowen Zhao Zhengyi Wang Hongyu Yan Wenqiang Zu Lei Ma and Jun Zhu. 2025b. NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.15019 (2025)."},{"key":"e_1_3_3_2_62_1","unstructured":"Chen-Yang Zhu Xin-Yao Liu Kai Xu and Ren-Jiao Yi. 2026. A survey on 3D editing based on NeRF and 3DGS. Frontiers of Computer Science (2026)."},{"key":"e_1_3_3_2_63_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. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201312.","DOI":"10.1145\/3658205"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618190"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:13:35Z","timestamp":1784225615000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":63,"alternative-id":["10.1145\/3799902.3811141","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811141","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}