{"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/multimodal-deep-learning-for-robust-rgb-d","title":"Multimodal Deep Learning for Robust RGB-D Object Recognition","arxiv_id":"1507.06821","date":"2015-07-24","proceeding":null,"authors":["Andreas Eitel","Jost Tobias Springenberg","Luciano Spinello","Martin Riedmiller","Wolfram Burgard"],"abstract":"Robust object recognition is a crucial ingredient of many, if not all,\nreal-world robotics applications. This paper leverages recent progress on\nConvolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture\nfor object recognition. Our architecture is composed of two separate CNN\nprocessing streams - one for each modality - which are consecutively combined\nwith a late fusion network. We focus on learning with imperfect sensor data, a\ntypical problem in real-world robotics tasks. For accurate learning, we\nintroduce a multi-stage training methodology and two crucial ingredients for\nhandling depth data with CNNs. The first, an effective encoding of depth\ninformation for CNNs that enables learning without the need for large depth\ndatasets. The second, a data augmentation scheme for robust learning with depth\nimages by corrupting them with realistic noise patterns. We present\nstate-of-the-art results on the RGB-D object dataset and show recognition in\nchallenging RGB-D real-world noisy settings.","url_abs":"http://arxiv.org/abs/1507.06821v2","url_pdf":"http://arxiv.org/pdf/1507.06821v2.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":"multimodal-deep-learning-for-robust-rgb-d","repo_url":"https://github.com/athar71/Object_Detection_Enhancement_with_RBG-D_Data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multimodal-deep-learning-for-robust-rgb-d","repo_url":"https://github.com/isrugeek/robotics_recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"multimodal-deep-learning","task_name":"Multimodal Deep Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1507.06821","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}