{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T02:09:17Z","timestamp":1774058957550,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"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":"NSERC Discovery","award":["RGPIN?2022?04680"],"award-info":[{"award-number":["RGPIN?2022?04680"]}]},{"name":"Ontario Early Research Award program"},{"name":"Canada Research Chairs Program"},{"name":"Sloan Research Fellowship"},{"name":"DSI Catalyst Grant program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687630","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Text-guided Controllable Mesh Refinement for Interactive 3D Modeling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0252-7503","authenticated-orcid":false,"given":"Yun-Chun","family":"Chen","sequence":"first","affiliation":[{"name":"University of Toronto, Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6458-4488","authenticated-orcid":false,"given":"Selena","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7835-1618","authenticated-orcid":false,"given":"Zhiqin","family":"Chen","sequence":"additional","affiliation":[{"name":"Adobe Research, Seattle, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3996-6588","authenticated-orcid":false,"given":"Vladimir G.","family":"Kim","sequence":"additional","affiliation":[{"name":"Adobe Research, Seattle, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4971-7980","authenticated-orcid":false,"given":"Matheus","family":"Gadelha","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-7143","authenticated-orcid":false,"given":"Alec","family":"Jacobson","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, Canada"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Sema Berkiten Maciej Halber Justin Solomon Chongyang Ma Hao Li and Szymon Rusinkiewicz. 2017. Learning detail transfer based on geometric features. Computer Graphics Forum (2017).","DOI":"10.1111\/cgf.13132"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618201"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591531"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01548"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Maximilian Denninger Dominik Winkelbauer Martin Sundermeyer Wout Boerdijk Markus\u00a0Wendelin Knauer Klaus\u00a0H Strobl Matthias Humt and Rudolph Triebel. 2023. Blenderproc2: A procedural pipeline for photorealistic rendering. Journal of Open Source Software (2023).","DOI":"10.21105\/joss.04901"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"crossref","unstructured":"Stefan Elfwing Eiji Uchibe and Kenji Doya. 2018. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks (2018).","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591552"},{"key":"e_1_3_3_2_12_1","unstructured":"Yuan-Chen Guo Ying-Tian Liu Ruizhi Shao Christian Laforte Vikram Voleti Guan Luo Chia-Hao Chen Zi-Xin Zou Chen Wang Yan-Pei Cao and Song-Hai Zhang. 2023. threestudio: A unified framework for 3D content generation. https:\/\/github.com\/threestudio-project\/threestudio."},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Amir Hertz Rana Hanocka Raja Giryes and Daniel Cohen-Or. 2020. Deep geometric texture synthesis. ACM Transactions on Graphics (2020).","DOI":"10.1145\/3386569.3392471"},{"key":"e_1_3_3_2_14_1","volume-title":"ICLR","author":"Hong Yicong","year":"2023","unstructured":"Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2023. LRM: Large Reconstruction Model for Single Image to 3D. In ICLR."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_3_2_16_1","volume-title":"ACM SIGGRAPH Asia","author":"Khalid Nasir\u00a0Mohammad","year":"2022","unstructured":"Nasir\u00a0Mohammad Khalid, Tianhao Xie, Eugene Belilovsky, and Tiberiu Popa. 2022. Clip-mesh: Generating textured meshes from text using pretrained image-text models. In ACM SIGGRAPH Asia."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Kiriakos\u00a0N Kutulakos and Steven\u00a0M Seitz. 2000. A theory of shape by space carving. IJCV (2000).","DOI":"10.1109\/ICCV.1999.791235"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Samuli Laine Janne Hellsten Tero Karras Yeongho Seol Jaakko Lehtinen and Timo Aila. 2020. Modular primitives for high-performance differentiable rendering. ACM Transactions on Graphics (2020).","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_3_3_2_20_1","volume-title":"ICLR","author":"Li Jiahao","year":"2023","unstructured":"Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, and Sai Bi. 2023. Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model. In ICLR."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_2_22_1","unstructured":"Hsueh-Ti\u00a0Derek Liu Vladimir\u00a0G Kim Siddhartha Chaudhuri Noam Aigerman and Alec Jacobson. 2020. Neural subdivision. ACM Transactions on Graphics (2020)."},{"key":"e_1_3_3_2_23_1","unstructured":"Hsueh-Ti\u00a0Derek Liu Michael Tao and Alec Jacobson. 2018. Paparazzi: surface editing by way of multi-view image processing. ACM Transactions on Graphics (2018)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"e_1_3_3_2_25_1","volume-title":"NeurIPS","author":"Liu Minghua","year":"2023","unstructured":"Minghua Liu, Chao Xu, Haian Jin, Linghao Chen, Mukund Varma\u00a0T, Zexiang Xu, and Hao Su. 2023b. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. In NeurIPS."},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_3_2_27_1","volume-title":"ICLR","author":"Liu Yuan","year":"2024","unstructured":"Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, and Wenping Wang. 2024a. Syncdreamer: Generating multiview-consistent images from a single-view image. In ICLR."},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"e_1_3_3_2_30_1","volume-title":"CVPR","author":"Lu Yuanxun","year":"2024","unstructured":"Yuanxun Lu, Jingyang Zhang, Shiwei Li, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Xun Cao, and Yao Yao. 2024. Direct2. 5: Diverse text-to-3d generation via multi-view 2.5 d diffusion. In CVPR."},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"e_1_3_3_2_33_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 (2021).","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Thomas M\u00fcller Alex Evans Christoph Schied and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (2022).","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Werner Palfinger. 2022. Continuous remeshing for inverse rendering. Computer Animation and Virtual Worlds (2022).","DOI":"10.1002\/cav.2101"},{"key":"e_1_3_3_2_37_1","volume-title":"ICLR","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T Barron, and Ben Mildenhall. 2023. Dreamfusion: Text-to-3d using 2d diffusion. In ICLR."},{"key":"e_1_3_3_2_38_1","volume-title":"ICLR","author":"Qian Guocheng","year":"2024","unstructured":"Guocheng Qian, Jinjie Mai, Abdullah Hamdi, Jian Ren, Aliaksandr Siarohin, Bing Li, Hsin-Ying Lee, Ivan Skorokhodov, Peter Wonka, Sergey Tulyakov, et\u00a0al. 2024. Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors. In ICLR."},{"key":"e_1_3_3_2_39_1","volume-title":"ICML","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In ICML."},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_42_1","volume-title":"NeurIPS","author":"Shen Tianchang","year":"2021","unstructured":"Tianchang Shen, Jun Gao, Kangxue Yin, Ming-Yu Liu, and Sanja Fidler. 2021. Deep Marching Tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. In NeurIPS."},{"key":"e_1_3_3_2_43_1","unstructured":"Ruoxi Shi Hansheng Chen Zhuoyang Zhang Minghua Liu Chao Xu Xinyue Wei Linghao Chen Chong Zeng and Hao Su. 2023. Zero123++: a single image to consistent multi-view diffusion base model. arXiv (2023)."},{"key":"e_1_3_3_2_44_1","volume-title":"ICLR","author":"Shi Yichun","year":"2024","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, and Xiao Yang. 2024. Mvdream: Multi-view diffusion for 3d generation. In ICLR."},{"key":"e_1_3_3_2_45_1","volume-title":"ICLR","author":"Tang Jiaxiang","year":"2023","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2023a. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. In ICLR."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"e_1_3_3_2_48_1","volume-title":"NeurIPS","author":"Wang Peng","year":"2021","unstructured":"Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. In NeurIPS."},{"key":"e_1_3_3_2_49_1","volume-title":"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 NeurIPS."},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"crossref","unstructured":"Hao Xu Yiqian Wu Xiangjun Tang Jing Zhang Yang Zhang Zhebin Zhang Chen Li and Xiaogang Jin. 2024. FusionDeformer: text-guided mesh deformation using diffusion models. The Visual Computer (2024).","DOI":"10.1007\/s00371-024-03463-7"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00151"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_53_1","unstructured":"SUN Zhengwentai. 2023. clip-score: CLIP Score for PyTorch. https:\/\/github.com\/taited\/clip-score."},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/1179352.1141942"}],"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\/3680528.3687630","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:27Z","timestamp":1750294707000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":53,"alternative-id":["10.1145\/3680528.3687630","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687630","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"}}]}}