{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:08Z","timestamp":1784228708124,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"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"}],"funder":[{"name":"Shenzhen Innovation and Entrepreneurship Plan","award":["KJZD20230923114114028"],"award-info":[{"award-number":["KJZD20230923114114028"]}]},{"name":"Shenzhen Innovation and Entrepreneurship Plan","award":["20232910020"],"award-info":[{"award-number":["20232910020"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811174","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8523-5606","authenticated-orcid":false,"given":"Shiyu","family":"Tan","sequence":"first","affiliation":[{"name":"School of Software and BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3372-4242","authenticated-orcid":false,"given":"Zixuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software and BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5340-2714","authenticated-orcid":false,"given":"Hao","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Software and BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6804-294X","authenticated-orcid":false,"given":"Zhiheng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software and BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2199-0932","authenticated-orcid":false,"given":"Xiaolong","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software and BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9303-969X","authenticated-orcid":false,"given":"Enya","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Software and BNRist, Tsinghua University, Beijing, China and Haihe Lab of ITAI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Md\u00a0Ferdous Alam and Faez Ahmed. 2024. Gencad: Image-conditioned computer-aided design generation with transformer-based contrastive representation and diffusion priors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.16294 (2024)."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"crossref","unstructured":"Kenneth Atz Francesca Grisoni and Gisbert Schneider. 2021. Geometric deep learning on molecular representations. Nature Machine Intelligence 3 12 (2021) 1023\u20131032.","DOI":"10.1038\/s42256-021-00418-8"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Michael\u00a0M Bronstein Joan Bruna Yann LeCun Arthur Szlam and Pierre Vandergheynst. 2017. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine 34 4 (2017) 18\u201342.","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Wenming Cao Zhiyue Yan Zhiquan He and Zhihai He. 2020. A comprehensive survey on geometric deep learning. IEEE Access 8 (2020) 35929\u201335949.","DOI":"10.1109\/ACCESS.2020.2975067"},{"key":"e_1_3_3_2_6_1","unstructured":"Angel\u00a0X Chang Thomas Funkhouser Leonidas Guibas Pat Hanrahan Qixing Huang Zimo Li Silvio Savarese Manolis Savva Shuran Song Hao Su et\u00a0al. 2015. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1512.03012 (2015)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01034"},{"key":"e_1_3_3_2_8_1","first-page":"19","volume-title":"European Conference on Computer Vision","author":"Dupont Elona","year":"2024","unstructured":"Elona Dupont, Kseniya Cherenkova, Dimitrios Mallis, Gleb Gusev, Anis Kacem, and Djamila Aouada. 2024. Transcad: A hierarchical transformer for cad sequence inference from point clouds. In European Conference on Computer Vision. Springer, 19\u201336."},{"key":"e_1_3_3_2_9_1","unstructured":"Xianze Fang Jingnan Gao Zhe Wang Zhuo Chen Xingyu Ren Jiangjing Lyu Qiaomu Ren Zhonglei Yang Xiaokang Yang Yichao Yan et\u00a0al. 2025. Dens3r: A foundation model for 3d geometry prediction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.16290 (2025)."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Jing-En Jiang Hanxiao Wang Mingyang Zhao Dong-Ming Yan Shuangmin Chen Shiqing Xin Changhe Tu and Wenping Wang. 2025. Defillet: Detection and removal of fillet regions in polygonal cad models. ACM Transactions on Graphics (TOG) 44 4 (2025) 1\u201319.","DOI":"10.1145\/3731166"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"David\u00a0J Kasik William Buxton and David\u00a0R Ferguson. 2005. Ten CAD challenges. IEEE Computer Graphics and Applications 25 2 (2005) 81\u201392.","DOI":"10.1109\/MCG.2005.48"},{"key":"e_1_3_3_2_13_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 Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR62088.2024.00021"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00983"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730698"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01997"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01730"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Pu Li Wenhao Zhang Weize Quan Biao Zhang Peter Wonka and Dongming Yan. 2025d. BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch. ACM Transactions on Graphics (TOG) 44 6 (2025) 1\u201318.","DOI":"10.1145\/3763323"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01998"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591522"},{"key":"e_1_3_3_2_22_1","unstructured":"Jinwei Lin. 2024. Dynamic nerf: A review. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.08609 (2024)."},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00361"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Yilin Liu Duoteng Xu Xingyao Yu Xiang Xu Daniel Cohen-Or Hao Zhang and Hui Huang. 2025. Hola: B-rep generation using a holistic latent representation. ACM Transactions on Graphics (TOG) 44 4 (2025) 1\u201325.","DOI":"10.1145\/3730842"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Takashi Miyazaki Yasuhiro Hotta Jun Kunii Soichi Kuriyama and Yukimichi Tamaki. 2009. A review of dental CAD\/CAM: current status and future perspectives from 20 years of experience. Dental materials journal 28 1 (2009) 44\u201356.","DOI":"10.4012\/dmj.28.44"},{"key":"e_1_3_3_2_28_1","volume-title":"The NURBS book","author":"Piegl Les","year":"2012","unstructured":"Les Piegl and Wayne Tiller. 2012. The NURBS book. Springer Science & Business Media."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/566282.566283"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Gerhard Roth and Martin\u00a0D Levine. 1993. Extracting geometric primitives. CVGIP: image understanding 58 1 (1993) 1\u201322.","DOI":"10.1006\/ciun.1993.1028"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00914"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00578"},{"key":"e_1_3_3_2_33_1","unstructured":"Dmitry Tochilkin David Pankratz Zexiang Liu Zixuan Huang Adam Letts Yangguang Li Ding Liang Christian Laforte Varun Jampani and Yan-Pei Cao. 2024. Triposr: Fast 3d object reconstruction from a single image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.02151 (2024)."},{"key":"e_1_3_3_2_34_1","unstructured":"Aaron Van Den\u00a0Oord Oriol Vinyals et\u00a0al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Willemien Visser. 2006. Designing as construction of representations: A dynamic viewpoint in cognitive design research. Human\u2013Computer Interaction 21 1 (2006) 103\u2013152.","DOI":"10.1207\/s15327051hci2101_4"},{"key":"e_1_3_3_2_36_1","first-page":"6772","volume-title":"CVF International Conference on Computer Vision (ICCV)","author":"Wu Rundi","year":"2021","unstructured":"Rundi Wu, Chang Xiao, and Changxi Zheng. 2021. Deepcad: A deep generative network for computer-aided design models. in 2021 ieee. In CVF International Conference on Computer Vision (ICCV). 6772\u20136782."},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"crossref","unstructured":"Shaobo Xia Dong Chen Ruisheng Wang Jonathan Li and Xinchang Zhang. 2020. Geometric primitives in LiDAR point clouds: A review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 13 (2020) 685\u2013707.","DOI":"10.1109\/JSTARS.2020.2969119"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887626"},{"key":"e_1_3_3_2_39_1","unstructured":"Jingwei Xu Chenyu Wang Zibo Zhao Wen Liu Yi Ma and Shenghua Gao. 2024. Cad-mllm: Unifying multimodality-conditioned cad generation with mllm. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.04954 (2024)."},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763814"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3620009"},{"key":"e_1_3_3_2_42_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML)","author":"Xu Xiang","year":"2022","unstructured":"Xiang Xu, Karl\u00a0D.D. Willis, Joseph\u00a0G Lambourne, Chin-Yi Cheng, Pradeep\u00a0Kumar Jayaraman, and Yasutaka Furukawa. 2022. SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks. In Proceedings of the 39th International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_43_1","unstructured":"Siming Yan Zhenpei Yang Chongyang Ma Haibin Huang Etienne Vouga and Qixing Huang. 2021. HPNet: Deep Primitive Segmentation Using Hybrid Representations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2105.10620 (2021)."},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Yingyu Yang Xiaohong Jia Bolun Wang Jieyin Yang Shiqing Xin and Dong\u00a0Ming Yan. 2025. Boolean Operation for CAD Models Using a Hybrid Representation. Transactions on Graphics 44 4 (2025).","DOI":"10.1145\/3730908"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763891"},{"key":"e_1_3_3_2_46_1","volume-title":"International Conference on Learning Representations (ICLR) 2025","author":"Zhang Zhanwei","year":"2025","unstructured":"Zhanwei Zhang, Shizhao Sun, Wenxiao Wang, Deng Cai, and Jiang Bian. 2025. FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models. In International Conference on Learning Representations (ICLR) 2025. https:\/\/arxiv.org\/abs\/2411.05823 arXiv:https:\/\/arXiv.org\/abs\/2411.05823."}],"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":"2026-07-16T18:16:29Z","timestamp":1784225789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":45,"alternative-id":["10.1145\/3799902.3811174","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811174","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"}}]}}