{"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/fast-scene-understanding-for-autonomous","title":"Fast Scene Understanding for Autonomous Driving","arxiv_id":"1708.02550","date":"2017-08-08","proceeding":null,"authors":["Davy Neven","Bert de Brabandere","Stamatios Georgoulis","Marc Proesmans","Luc van Gool"],"abstract":"Most approaches for instance-aware semantic labeling traditionally focus on\naccuracy. Other aspects like runtime and memory footprint are arguably as\nimportant for real-time applications such as autonomous driving. Motivated by\nthis observation and inspired by recent works that tackle multiple tasks with a\nsingle integrated architecture, in this paper we present a real-time efficient\nimplementation based on ENet that solves three autonomous driving related tasks\nat once: semantic scene segmentation, instance segmentation and monocular depth\nestimation. Our approach builds upon a branched ENet architecture with a shared\nencoder but different decoder branches for each of the three tasks. The\npresented method can run at 21 fps at a resolution of 1024x512 on the\nCityscapes dataset without sacrificing accuracy compared to running each task\nseparately.","url_abs":"http://arxiv.org/abs/1708.02550v1","url_pdf":"http://arxiv.org/pdf/1708.02550v1.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":"fast-scene-understanding-for-autonomous","repo_url":"https://github.com/davyneven/fastSceneUnderstanding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"scene-segmentation","task_name":"Scene Segmentation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"enet","method_name":"ENet"},{"method_slug":"enet-bottleneck","method_name":"ENet Bottleneck"},{"method_slug":"enet-dilated-bottleneck","method_name":"ENet Dilated Bottleneck"},{"method_slug":"enet-initial-block","method_name":"ENet Initial Block"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"prelu","method_name":"PReLU"},{"method_slug":"spatialdropout","method_name":"SpatialDropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.02550","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}