{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:30Z","timestamp":1777888770404,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100006465","name":"Korea Creative Content Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003561","name":"Ministry of Culture, Sports and Tourism","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003561","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02621","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28228-28238","source":"Crossref","is-referenced-by-count":0,"title":["CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from a Single-View Image"],"prefix":"10.1109","author":[{"given":"Wonseok","family":"Roh","sequence":"first","affiliation":[{"name":"Korea University"}]},{"given":"Hwanhee","family":"Jung","sequence":"additional","affiliation":[{"name":"Korea University"}]},{"given":"Jong Wook","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University"}]},{"given":"Seunggwan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University"}]},{"given":"Innfarn","family":"Yoo","sequence":"additional","affiliation":[{"name":"CNAPS.AI Inc."}]},{"given":"Andreas","family":"Lugmayr","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Seunggeun","family":"Chi","sequence":"additional","affiliation":[{"name":"Purdue University"}]},{"given":"Karthik","family":"Ramani","sequence":"additional","affiliation":[{"name":"Purdue University"}]},{"given":"Sangpil","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150497"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","article-title":"Palm 2 technical report","author":"Anil","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"5855","article-title":"Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Jonathan","year":"2021"},{"key":"ref6","article-title":"Language models are few-shot learners","author":"Brown","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"issue":"3","key":"ref10","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"issue":"70","key":"ref11","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3408318"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/0600000105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00277"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref21","article-title":"Generating images with multimodal language models","author":"Yu Koh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01235"},{"key":"ref24","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref25","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","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_23"},{"key":"ref28","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/773"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref35","article-title":"Improving multimodal datasets with image captioning","author":"Nguyen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09661"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00067"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref46","article-title":"Volume rendering digest (for nerf)","author":"Tagliasacchi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_27"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00876"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00798"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01922"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref58","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33070"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348297"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref65","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00841"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445181.pdf?arnumber=11445181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:23Z","timestamp":1777611323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02621","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}