{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/modeling-camera-effects-to-improve-visual","title":"Modeling Camera Effects to Improve Visual Learning from Synthetic Data","arxiv_id":"1803.07721","date":"2018-03-21","proceeding":null,"authors":["Alexandra Carlson","Katherine A. Skinner","Ram Vasudevan","Matthew Johnson-Roberson"],"abstract":"Recent work has focused on generating synthetic imagery to increase the size\nand variability of training data for learning visual tasks in urban scenes.\nThis includes increasing the occurrence of occlusions or varying environmental\nand weather effects. However, few have addressed modeling variation in the\nsensor domain. Sensor effects can degrade real images, limiting\ngeneralizability of network performance on visual tasks trained on synthetic\ndata and tested in real environments. This paper proposes an efficient,\nautomatic, physically-based augmentation pipeline to vary sensor effects\n--chromatic aberration, blur, exposure, noise, and color cast-- for synthetic\nimagery. In particular, this paper illustrates that augmenting synthetic\ntraining datasets with the proposed pipeline reduces the domain gap between\nsynthetic and real domains for the task of object detection in urban driving\nscenes.","url_abs":"http://arxiv.org/abs/1803.07721v6","url_pdf":"http://arxiv.org/pdf/1803.07721v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"modeling-camera-effects-to-improve-visual","repo_url":"https://github.com/alexacarlson/SensorEffectAugmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}