{"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/semantically-meaningful-view-selection","title":"Semantically Meaningful View Selection","arxiv_id":"1807.10303","date":"2018-07-26","proceeding":null,"authors":["Joris Guérin","Olivier Gibaru","Eric Nyiri","Stéphane Thiery","Byron Boots"],"abstract":"An understanding of the nature of objects could help robots to solve both\nhigh-level abstract tasks and improve performance at lower-level concrete\ntasks. Although deep learning has facilitated progress in image understanding,\na robot's performance in problems like object recognition often depends on the\nangle from which the object is observed. Traditionally, robot sorting tasks\nrely on a fixed top-down view of an object. By changing its viewing angle, a\nrobot can select a more semantically informative view leading to better\nperformance for object recognition. In this paper, we introduce the problem of\nsemantic view selection, which seeks to find good camera poses to gain semantic\nknowledge about an observed object. We propose a conceptual formulation of the\nproblem, together with a solvable relaxation based on clustering. We then\npresent a new image dataset consisting of around 10k images representing\nvarious views of 144 objects under different poses. Finally we use this dataset\nto propose a first solution to the problem by training a neural network to\npredict a \"semantic score\" from a top view image and camera pose. The views\npredicted to have higher scores are then shown to provide better clustering\nresults than fixed top-down views.","url_abs":"http://arxiv.org/abs/1807.10303v1","url_pdf":"http://arxiv.org/pdf/1807.10303v1.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":"semantically-meaningful-view-selection","repo_url":"https://github.com/jorisguerin/SemanticViewSelection_dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}