{"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/irs-a-large-synthetic-indoor-robotics-stereo","title":"IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation","arxiv_id":"1912.09678","date":"2019-12-20","proceeding":null,"authors":["Qiang Wang","Shizhen Zheng","Qingsong Yan","Fei Deng","Kaiyong Zhao","Xiaowen Chu"],"abstract":"Indoor robotics localization, navigation, and interaction heavily rely on scene understanding and reconstruction. Compared to the monocular vision which usually does not explicitly introduce any geometrical constraint, stereo vision-based schemes are more promising and robust to produce accurate geometrical information, such as surface normal and depth/disparity. Besides, deep learning models trained with large-scale datasets have shown their superior performance in many stereo vision tasks. However, existing stereo datasets rarely contain the high-quality surface normal and disparity ground truth, which hardly satisfies the demand of training a prospective deep model for indoor scenes. To this end, we introduce a large-scale synthetic but naturalistic indoor robotics stereo (IRS) dataset with over 100K stereo RGB images and high-quality surface normal and disparity maps. Leveraging the advanced rendering techniques of our customized rendering engine, the dataset is considerably close to the real-world captured images and covers several visual effects, such as brightness changes, light reflection/transmission, lens flare, vivid shadow, etc. We compare the data distribution of IRS with existing stereo datasets to illustrate the typical visual attributes of indoor scenes. Besides, we present DTN-Net, a two-stage deep model for surface normal estimation. Extensive experiments show the advantages and effectiveness of IRS in training deep models for disparity estimation, and DTN-Net provides state-of-the-art results for normal estimation compared to existing methods.","url_abs":"https://arxiv.org/abs/1912.09678v2","url_pdf":"https://arxiv.org/pdf/1912.09678v2.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":"irs-a-large-synthetic-indoor-robotics-stereo","repo_url":"https://github.com/HKBU-HPML/IRS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"}],"methods":[],"datasets_introduced":[{"slug":"irs","name":"IRS","full_name":"Indoor Robotics Stereo"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.09678","atlas_url":"https://app.syntology.ai/?focus=1912.09678","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}