{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T00:32:29Z","timestamp":1760747549789,"version":"build-2065373602"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Technology Innovation Program"},{"name":"Ministry of Trade, Industry & Energy","award":["RS-2024-00423940"],"award-info":[{"award-number":["RS-2024-00423940"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/lra.2025.3615035","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:38:29Z","timestamp":1758908309000},"page":"12039-12046","source":"Crossref","is-referenced-by-count":0,"title":["Single-View 3D-Aware Representations for Reinforcement Learning by Cross-View Neural Radiance Fields"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4105-4422","authenticated-orcid":false,"given":"Daesol","family":"Cho","sequence":"first","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3999-588X","authenticated-orcid":false,"given":"Seungyeon","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1580-0716","authenticated-orcid":false,"given":"Dongseok","family":"Shim","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in AI, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6819-1136","authenticated-orcid":false,"given":"H. Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"article-title":"R3M: A universal visual representation for robot manipulation","year":"2022","author":"Nair","key":"ref2"},{"article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","year":"2021","author":"Yarats","key":"ref3"},{"key":"ref4","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats","year":"2021"},{"key":"ref5","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Proc. Conf. Robot Learn.","author":"Seo","year":"2023"},{"article-title":"Masked visual pre-training for motor control","year":"2022","author":"Xiao","key":"ref6"},{"article-title":"VIP: Towards universal visual reward and representation via value-implicit pre-training","year":"2022","author":"Ma","key":"ref7"},{"key":"ref8","first-page":"11321","article-title":"Reinforcement learning from passive data via latent intentions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghosh","year":"2023"},{"article-title":"3D diffuser actor: Policy diffusion with 3D scene representations","year":"2024","author":"Ke","key":"ref9"},{"key":"ref10","first-page":"3949","article-title":"Act3D: 3D feature field transformers for multi-task robotic manipulation","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Gervet","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.055"},{"key":"ref12","first-page":"16931","article-title":"Reinforcement learning with neural radiance fields","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Driess","year":"2022"},{"key":"ref13","first-page":"31489","article-title":"SNeRL: Semantic-aware neural radiance fields for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shim","year":"2023"},{"key":"ref14","first-page":"112","article-title":"3D neural scene representations for visuomotor control","volume-title":"Proc. Conf. Robot Learn.","author":"Li","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref19","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yarats","year":"2021"},{"key":"ref20","first-page":"6736","article-title":"APS: Active pretraining with successor features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref21","first-page":"18459","article-title":"Behavior from the void: Unsupervised active pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2021"},{"key":"ref22","first-page":"9209","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nair","year":"2018"},{"key":"ref23","first-page":"632","article-title":"Multi-view masked world models for visual robotic manipulation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"30","author":"Seo","year":"2023"},{"key":"ref24","first-page":"19561","article-title":"Reinforcement learning with action-free pre-training from videos","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Seo","year":"2022"},{"article-title":"Dream to control: Learning behaviors by latent imagination","year":"2019","author":"Hafner","key":"ref25"},{"key":"ref26","first-page":"1539","article-title":"Unsupervised learning of visual 3D keypoints for control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2021"},{"key":"ref27","article-title":"Vision-based manipulators need to also see from their hands","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hsu","year":"2022"},{"key":"ref28","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02098"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.067"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"ref34","first-page":"3502","article-title":"CroCo: Self-supervised pre-training for 3D vision tasks by cross-view completion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Weinzaepfel","year":"2022"},{"key":"ref35","article-title":"DRM: Mastering visual reinforcement learning through dormant ratio minimization","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xu","year":"2024"},{"key":"ref36","article-title":"Flow Q-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Park","year":"2025"},{"key":"ref37","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00194"},{"article-title":"LRM: Large reconstruction model for single image to 3D","year":"2023","author":"Hong","key":"ref40"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11169302\/11180891.pdf?arnumber=11180891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:42:48Z","timestamp":1760722968000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11180891\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":40,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3615035","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}