{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:07:51Z","timestamp":1777655271345,"version":"3.51.4"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"National Science and Technology Major","award":["2022ZD0116305"],"award-info":[{"award-number":["2022ZD0116305"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172220"],"award-info":[{"award-number":["62172220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62361166670 and U24A20330"],"award-info":[{"award-number":["62361166670 and U24A20330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Supercomputing Center of Nankai University"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:p>\n            3D Gaussian Splatting (3DGS) has shown a powerful capability for novel view synthesis due to its detailed expressive ability and highly efficient rendering speed. Unfortunately, creating relightable 3D assets and reconstructing faithful geometry with 3DGS is still problematic, particularly for reflective objects, as its discontinuous representation raises difficulties in constraining geometries. In contrary, volumetric signed distance field (SDF) methods provide robust geometry reconstruction, while the expensive ray marching hinders its real-time application and slows the training. Besides, these methods struggle to capture sharp geometric details. To this end, we propose to guide 3DGS and SDF bidirectionally in a complementary manner, including an SDF-aided Gaussian splatting for efficient optimization of the relighting model and a GS-guided SDF enhancement for high-quality geometry reconstruction. At the core of our SDF-aided Gaussian splatting is the\n            <jats:italic toggle=\"yes\">mutual supervision<\/jats:italic>\n            of the depth and normal between blended Gaussians and SDF, which avoids the expensive volume rendering of SDF. Thanks to this mutual supervision, the learned blended Gaussians are well-constrained with a minimal time cost. As the Gaussians are rendered in a deferred shading mode, the alpha-blended Gaussians are smooth, while individual Gaussians may still be outliers, yielding floater artifacts. Therefore, we introduce an SDF-aware pruning strategy to remove Gaussian outliers located distant from the surface defined by SDF, avoiding the floater issue. This way, our GS framework provides reasonable normal and achieves realistic relighting, while the mesh of truncated SDF (TSDF) fusion from depth is still problematic. Therefore, we design a GS-guided SDF refinement, which utilizes the blended normal from Gaussians to finetune SDF. Equipped with the efficient enhancement, our method can further provide high-quality meshes for reflective objects at the cost of 17% extra training time. Consequently, our method outperforms the existing Gaussian-based inverse rendering methods in terms of relighting and mesh quality. Our method also exhibits competitive relighting\/mesh quality compared to NeRF-based methods with at most 25%\/33% of training time and allows rendering at 200+ frames per second on an RTX4090. Our code is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/NK-CS-ZZL\/GS-ROR\">https:\/\/github.com\/NK-CS-ZZL\/GS-ROR<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3759248","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T11:13:46Z","timestamp":1754565226000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction"],"prefix":"10.1145","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3588-4098","authenticated-orcid":false,"given":"Zuoliang","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Computer Science, Nankai University","place":["Tianjin, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8943-8364","authenticated-orcid":false,"given":"Beibei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University","place":["Suzhou, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University","place":["Tianjin, China"]}]}],"member":"320","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","unstructured":"Sai Bi Zexiang Xu Pratul Srinivasan Ben Mildenhall Kalyan Sunkavalli Milo\u0161 Ha\u0161an Yannick Hold-Geoffroy David Kriegman and Ravi Ramamoorthi. 2020. Neural reflectance fields for appearance acquisition. arXiv:2008.03824 10.48550\/arXiv.2008.03824","DOI":"10.48550\/arXiv.2008.03824"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01245"},{"key":"e_1_3_4_6_1","first-page":"10691","volume-title":"NeurIPS","author":"Boss Mark","year":"2021","unstructured":"Mark Boss, Varun Jampani, Raphael Braun, Ce Liu, Jonathan Barron, and Hendrik P. A. Lensch. 2021b. Neural-PIL: Neural pre-integrated lighting for reflectance decomposition. In NeurIPS. M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., Red Hook, NY, USA, 10691\u201310704."},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","unstructured":"Danpeng Chen Hai Li Weicai Ye Yifan Wang Weijian Xie Shangjin Zhai Nan Wang Haomin Liu Hujun Bao and Guofeng Zhang. 2025. PGSR: Planar-based Gaussian splatting for efficient and high-fidelity surface reconstruction. IEEE TVCG 31 9 (2025) 6100\u20136111. 10.1109\/TVCG.2024.3494046","DOI":"10.1109\/TVCG.2024.3494046"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","unstructured":"Hanlin Chen Chen Li and Gim Hee Lee. 2023. NeuSG: Neural implicit surface reconstruction with 3D Gaussian splatting guidance. arXiv:2312.00846 10.48550\/arXiv.2312.00846","DOI":"10.48550\/arXiv.2312.00846"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657441"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","unstructured":"Jian Gao Chun Gu Youtian Lin Zhihao Li Hao Zhu Xun Cao Li Zhang and Yao Yao. 2024. Relightable 3D Gaussians: Realistic point cloud relighting with BRDF decomposition and ray tracing. In ECCV. Springer-Verlag Berlin Heidelberg 73\u201389. 10.1007\/978-3-031-72995-9_5","DOI":"10.1007\/978-3-031-72995-9_5"},{"key":"e_1_3_4_13_1","volume-title":"ICML (ICML\u201920)","author":"Gropp Amos","year":"2020","unstructured":"Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, and Yaron Lipman. 2020. Implicit geometric regularization for learning shapes. In ICML (ICML\u201920). PMLR, New York, NY, USA, Article 355, 11 pages."},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00509"},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00024"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","unstructured":"Diederik P. Kingma and Jimmy Ba. 2017. Adam: A method for stochastic optimization. arXiv:1412.6980 10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"e_1_3_4_20_1","unstructured":"Zhengfei Kuang Yunzhi Zhang Hong-Xing Yu Samir Agarwala Shangzhe Wu and Jiajun Wu. 2023. Stanford-ORB: A real-world 3D object inverse rendering benchmark. In NeurIPS Vol. 36. Curran Associates Inc. Red Hook NY USA 46938\u201346957."},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","unstructured":"Shuichang Lai Letian Huang Jie Guo Kai Cheng Bowen Pan Xiaoxiao Long Jiangjing Lyu Chengfei Lv and Yanwen Guo. 2024. GlossyGS: Inverse rendering of glossy objects with 3D Gaussian splatting. IEEE TVCG 1 1 (2025) 1\u201314. 10.1109\/TVCG.2025.3547063","DOI":"10.1109\/TVCG.2025.3547063"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658211"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02045"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657404"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592134"},{"key":"e_1_3_4_28_1","doi-asserted-by":"crossref","unstructured":"Li Ma Vasu Agrawal Haithem Turki Changil Kim Chen Gao Pedro Sander Michael Zollh\u00f6fer and Christian Richardt. 2024. SpecNeRF: Gaussian directional encoding for specular reflections. In CVPR. IEEE New York NY USA 21188\u201321198.","DOI":"10.1109\/CVPR52733.2024.02002"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2504435.2504457"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687934"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_4_33_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 et\u00a0al. 2024. DINOv2: Learning robust visual features without supervision. TMLR 2024 (2024) 1\u201332."},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658187"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00818"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","unstructured":"Yahao Shi Yanmin Wu Chenming Wu Xing Liu Chen Zhao Haocheng Feng Jingtuo Liu Liangjun Zhang Jian Zhang Bin Zhou et\u00a0al. 2023. GIR: 3D Gaussian inverse rendering for relightable scene factorization. IEEE TPAMI 1 1 (2025) 1\u201312. 10.1109\/TPAMI.2025.3575937","DOI":"10.1109\/TPAMI.2025.3575937"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00741"},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01654"},{"key":"e_1_3_4_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00541"},{"key":"e_1_3_4_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01890"},{"key":"e_1_3_4_41_1","first-page":"27171","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. M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., Red Hook, NY, USA, 27171\u201327183."},{"issue":"4","key":"e_1_3_4_42_1","first-page":"600","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. 2004. Image quality assessment: From error visibility to structural similarity. IEEE TIP 13, 4 (2004), 600\u2013612.","journal-title":"IEEE TIP"},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618311"},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","unstructured":"Tong Wu Jia-Mu Sun Yu-Kun Lai Yuewen Ma Leif Kobbelt and Lin Gao. 2025. DeferredGS: Decoupled and editable gaussian splatting with deferred shading. IEEE TPAMI 47 8 (2025) 6307\u20136319. 10.1109\/TPAMI.2025.3560933","DOI":"10.1109\/TPAMI.2025.3560933"},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","unstructured":"Ziyi Yang Yanzhen Chen Xinyu Gao Yazhen Yuan Yu Wu Xiaowei Zhou and Xiaogang Jin. 2023. SIRe-IR: Inverse rendering for BRDF reconstruction with shadow and illumination removal in high-illuminance scenes. arXiv:2310.13030 10.48550\/arXiv.2310.13030","DOI":"10.48550\/arXiv.2310.13030"},{"key":"e_1_3_4_46_1","unstructured":"Ziyi Yang Xinyu Gao Yangtian Sun Yihua Huang Xiaoyang Lyu Wen Zhou Shaohui Jiao Xiaojuan Qi and Xiaogang Jin. 2024. Spec-Gaussian: Anisotropic view-dependent appearance for 3D Gaussian splatting. In NeurIPS A. Globerson L. Mackey D. Belgrave A. Fan U. Paquet J. Tomczak and C. Zhang (Eds.). Vol. 37. Curran Associates Inc. Red Hook NY USA 61192\u201361216."},{"key":"e_1_3_4_47_1","first-page":"4805","volume-title":"NeurIPS","author":"Yariv Lior","year":"2021","unstructured":"Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume rendering of neural implicit surfaces. In NeurIPS. M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., Red Hook, NY, USA, 4805\u20134815."},{"key":"e_1_3_4_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657456"},{"key":"e_1_3_4_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01194"},{"key":"e_1_3_4_50_1","unstructured":"Mulin Yu Tao Lu Linning Xu Lihan Jiang Yuanbo Xiangli and Bo Dai. 2024a. GSDF: 3DGS meets SDF for improved rendering and reconstruction. In NeurIPS A. Globerson L. Mackey D. Belgrave A. Fan U. Paquet J. Tomczak and C. Zhang (Eds.). Vol. 37. Curran Associates Inc. Red Hook NY USA 129507\u2013129530."},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687937"},{"key":"e_1_3_4_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00617"},{"key":"e_1_3_4_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00333"},{"key":"e_1_3_4_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00548"},{"key":"e_1_3_4_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00541"},{"key":"e_1_3_4_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_4_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480496"},{"key":"e_1_3_4_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01809"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3759248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T12:19:51Z","timestamp":1757593191000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3759248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"references-count":57,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2,28]]}},"alternative-id":["10.1145\/3759248"],"URL":"https:\/\/doi.org\/10.1145\/3759248","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"assertion":[{"value":"2024-09-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}