Building a database of 3D scenes from user annotations
In this paper, we wish to build a high quality database of images depicting scenes, along with their real-world three-dimensional (3D) coordinates. Such a database is useful for a variety of applications, including training systems for object detection and validation of 3D output. We build such a da...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| Online Access: | http://hdl.handle.net/1721.1/60053 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1826217392656613376 |
|---|---|
| author | Russell, Bryan C. Torralba, Antonio |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Russell, Bryan C. Torralba, Antonio |
| author_sort | Russell, Bryan C. |
| collection | MIT |
| description | In this paper, we wish to build a high quality database of images depicting scenes, along with their real-world three-dimensional (3D) coordinates. Such a database is useful for a variety of applications, including training systems for object detection and validation of 3D output. We build such a database from images that have been annotated with only the identity of objects and their spatial extent in images. Important for this task is the recovery of geometric information that is implicit in the object labels, such as qualitative relationships between objects (attachment, support, occlusion) and quantitative ones (inferring camera parameters). We describe a model that integrates cues extracted from the object labels to infer the implicit geometric information. We show that we are able to obtain high quality 3D information by evaluating the proposed approach on a database obtained with a laser range scanner. Finally, given the database of 3D scenes, we show how it can find better scene matches for an unlabeled image by expanding the database through viewpoint interpolation to unseen views. |
| first_indexed | 2024-09-23T17:02:56Z |
| format | Article |
| id | mit-1721.1/60053 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T17:02:56Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/600532022-10-03T10:02:51Z Building a database of 3D scenes from user annotations Russell, Bryan C. Torralba, Antonio Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Torralba, Antonio Torralba, Antonio In this paper, we wish to build a high quality database of images depicting scenes, along with their real-world three-dimensional (3D) coordinates. Such a database is useful for a variety of applications, including training systems for object detection and validation of 3D output. We build such a database from images that have been annotated with only the identity of objects and their spatial extent in images. Important for this task is the recovery of geometric information that is implicit in the object labels, such as qualitative relationships between objects (attachment, support, occlusion) and quantitative ones (inferring camera parameters). We describe a model that integrates cues extracted from the object labels to infer the implicit geometric information. We show that we are able to obtain high quality 3D information by evaluating the proposed approach on a database obtained with a laser range scanner. Finally, given the database of 3D scenes, we show how it can find better scene matches for an unlabeled image by expanding the database through viewpoint interpolation to unseen views. National Science Foundation (U.S.) (CAREER award IIS 0747120) 2010-12-02T14:11:08Z 2010-12-02T14:11:08Z 2009-08 2009-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-3992-8 1063-6919 INSPEC Accession Number: 10835842 http://hdl.handle.net/1721.1/60053 Russell, B.C., and A. Torralba. “Building a database of 3D scenes from user annotations.” Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. 2009. 2711-2718. © Copyright 2009 IEEE https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/10.1109/CVPRW.2009.5206643 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009. Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Russell, Bryan C. Torralba, Antonio Building a database of 3D scenes from user annotations |
| title | Building a database of 3D scenes from user annotations |
| title_full | Building a database of 3D scenes from user annotations |
| title_fullStr | Building a database of 3D scenes from user annotations |
| title_full_unstemmed | Building a database of 3D scenes from user annotations |
| title_short | Building a database of 3D scenes from user annotations |
| title_sort | building a database of 3d scenes from user annotations |
| url | http://hdl.handle.net/1721.1/60053 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT russellbryanc buildingadatabaseof3dscenesfromuserannotations AT torralbaantonio buildingadatabaseof3dscenesfromuserannotations |