{"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/interiornet-mega-scale-multi-sensor-photo","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","arxiv_id":"1809.00716","date":"2018-09-03","proceeding":null,"authors":["Wenbin Li","Sajad Saeedi","John McCormac","Ronald Clark","Dimos Tzoumanikas","Qing Ye","Yuzhong Huang","Rui Tang","Stefan Leutenegger"],"abstract":"Datasets have gained an enormous amount of popularity in the computer vision\ncommunity, from training and evaluation of Deep Learning-based methods to\nbenchmarking Simultaneous Localization and Mapping (SLAM). Without a doubt,\nsynthetic imagery bears a vast potential due to scalability in terms of amounts\nof data obtainable without tedious manual ground truth annotations or\nmeasurements. Here, we present a dataset with the aim of providing a higher\ndegree of photo-realism, larger scale, more variability as well as serving a\nwider range of purposes compared to existing datasets. Our dataset leverages\nthe availability of millions of professional interior designs and millions of\nproduction-level furniture and object assets -- all coming with fine geometric\ndetails and high-resolution texture. We render high-resolution and high\nframe-rate video sequences following realistic trajectories while supporting\nvarious camera types as well as providing inertial measurements. Together with\nthe release of the dataset, we will make executable program of our interactive\nsimulator software as well as our renderer available at\nhttps://interiornetdataset.github.io. To showcase the usability and uniqueness\nof our dataset, we show benchmarking results of both sparse and dense SLAM\nalgorithms.","url_abs":"http://arxiv.org/abs/1809.00716v1","url_pdf":"http://arxiv.org/pdf/1809.00716v1.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":[],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"simultaneous-localization-and-mapping","task_name":"Simultaneous Localization and Mapping"}],"methods":[],"datasets_introduced":[{"slug":"interiornet","name":"InteriorNet","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00716","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}