{"page":"1060–1072","date_updated":"2023-06-17T09:25:09Z","intvolume":"       131","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://link.springer.com/article/10.1007/s11263-022-01725-2","open_access":"1"}],"type":"journal_article","publication_identifier":{"issn":["0920-5691"],"eissn":["1573-1405"]},"abstract":[{"text":"                  Abstract - \r\n                  In this work, we focus on outdoor lighting estimation by aggregating individual noisy estimates from images, exploiting the rich image information from wide-angle cameras and/or temporal image sequences. Photographs inherently encode information about the lighting of the scene in the form of shading and shadows. Recovering the lighting is an inverse rendering problem and as that ill-posed. Recent research based on deep neural networks has shown promising results for estimating light from a single image, but with shortcomings in robustness. We tackle this problem by combining lighting estimates from several image views sampled in the angular and temporal domains of an image sequence. For this task, we introduce a transformer architecture that is trained in an end-2-end fashion without any statistical post-processing as required by previous work. Thereby, we propose a positional encoding that takes into account camera alignment and ego-motion estimation to globally register the individual estimates when computing attention between visual words. We show that our method leads to improved lighting estimation while requiring fewer hyperparameters compared to the state of the art.\r\n                ","lang":"eng"}],"doi":"10.1007/s11263-022-01725-2","volume":131,"oa":"1","publisher":"Springer Science and Business Media LLC","author":[{"first_name":"Haebom","last_name":"Lee","full_name":"Lee, Haebom"},{"full_name":"Homeyer, Christian","last_name":"Homeyer","first_name":"Christian"},{"first_name":"Robert","last_name":"Herzog","full_name":"Herzog, Robert"},{"id":"245736","orcid":"0000-0002-4579-214X","first_name":"Jan","last_name":"Rexilius","full_name":"Rexilius, Jan"},{"first_name":"Carsten","full_name":"Rother, Carsten","last_name":"Rother"}],"_id":"2253","status":"public","title":"Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks","publication":"International Journal of Computer Vision","date_created":"2022-12-15T10:28:47Z","user_id":"216459","citation":{"bibtex":"@article{Lee_Homeyer_Herzog_Rexilius_Rother_2022, title={Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks}, volume={131}, DOI={<a href=\"https://doi.org/10.1007/s11263-022-01725-2\">10.1007/s11263-022-01725-2</a>}, journal={International Journal of Computer Vision}, publisher={Springer Science and Business Media LLC}, author={Lee, Haebom and Homeyer, Christian and Herzog, Robert and Rexilius, Jan and Rother, Carsten}, year={2022}, pages={1060–1072} }","mla":"Lee, Haebom, et al. “Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks.” <i>International Journal of Computer Vision</i>, vol. 131, Springer Science and Business Media LLC, 2022, pp. 1060–1072, doi:<a href=\"https://doi.org/10.1007/s11263-022-01725-2\">10.1007/s11263-022-01725-2</a>.","ama":"Lee H, Homeyer C, Herzog R, Rexilius J, Rother C. Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks. <i>International Journal of Computer Vision</i>. 2022;131:1060–1072. doi:<a href=\"https://doi.org/10.1007/s11263-022-01725-2\">10.1007/s11263-022-01725-2</a>","apa":"Lee, H., Homeyer, C., Herzog, R., Rexilius, J., &#38; Rother, C. (2022). Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks. <i>International Journal of Computer Vision</i>, <i>131</i>, 1060–1072. <a href=\"https://doi.org/10.1007/s11263-022-01725-2\">https://doi.org/10.1007/s11263-022-01725-2</a>","chicago":"Lee, Haebom, Christian Homeyer, Robert Herzog, Jan Rexilius, and Carsten Rother. “Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks.” <i>International Journal of Computer Vision</i> 131 (2022): 1060–1072. <a href=\"https://doi.org/10.1007/s11263-022-01725-2\">https://doi.org/10.1007/s11263-022-01725-2</a>.","ieee":"H. Lee, C. Homeyer, R. Herzog, J. Rexilius, and C. Rother, “Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks,” <i>International Journal of Computer Vision</i>, vol. 131, pp. 1060–1072, 2022.","short":"H. Lee, C. Homeyer, R. Herzog, J. Rexilius, C. Rother, International Journal of Computer Vision 131 (2022) 1060–1072.","alphadin":"<span style=\"font-variant:small-caps;\">Lee, Haebom</span> ; <span style=\"font-variant:small-caps;\">Homeyer, Christian</span> ; <span style=\"font-variant:small-caps;\">Herzog, Robert</span> ; <span style=\"font-variant:small-caps;\">Rexilius, Jan</span> ; <span style=\"font-variant:small-caps;\">Rother, Carsten</span>: Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks. In: <i>International Journal of Computer Vision</i> Bd. 131, Springer Science and Business Media LLC (2022), S. 1060–1072"},"tmp":{"short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"publication_status":"published","year":"2022"}