{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:23:44Z","timestamp":1780392224557,"version":"3.54.1"},"reference-count":95,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00185","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1852-1863","source":"Crossref","is-referenced-by-count":1,"title":["3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting"],"prefix":"10.1109","author":[{"given":"Ziyang","family":"Yan","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihua","family":"Shao","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minwen","family":"Liao","sequence":"additional","affiliation":[{"name":"Xinjiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muyuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Remondino","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0160"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612489"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305295"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_17"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref14","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2686"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00665"},{"key":"ref18","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00076"},{"key":"ref20","article-title":"Semantic anything in 3d gaussians","author":"Hu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00513"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3585499"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00432"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref30","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02097-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128255"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref36","article-title":"One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2026.115367"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01882"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0810"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00018"},{"key":"ref49","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00223"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/rs15143585"},{"key":"ref53","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref58","article-title":"Gwq: Gradient-aware weight quantization for large language models","author":"Shao","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_26"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01323"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00714"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref63","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref66","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref67","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref68","article-title":"Instruct-gs2gs: Editing 3d gaussian splats with instructions","author":"Vachha","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_9"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01975"},{"key":"ref71","article-title":"Unifying appearance codes and bilateral grids for driving scene gaussian splatting","author":"Wang","year":"2025"},{"key":"ref72","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_25"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_4"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00509"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLVIII-1-W3-2023-219-2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127609"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/metrology5020020"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00027"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref82","article-title":"Gaussian-dreamer: Fast generation from text to 3d gaussian splatting with point cloud priors","author":"Yi","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref84","article-title":"Gaussiandreamerpro: Text to manipulable 3d gaussians with highly enhanced quality","author":"Yi","year":"2024"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612232"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01781"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref88","article-title":"Video-star: Reinforcing open-vocabulary action recognition with tools","author":"Yuan","year":"2025"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.12968\/s0013-7758(23)90464-2"},{"key":"ref90","article-title":"3DitScene: Editing any scene via language-guided disentangled gaussian splatting","author":"Zhang","year":"2024"},{"key":"ref91","article-title":"Spartun3d: Situated spatial understanding of 3d world in large language models","author":"Zhang","year":"2024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_11"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1185"},{"key":"ref94","article-title":"Llava-3d: A simple yet effective pathway to empowering lmms with 3d-awareness","author":"Zhu","year":"2024"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_9"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492578.pdf?arnumber=11492578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:58:12Z","timestamp":1778047092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00185","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}