Shape Anchors for Data-Driven Multi-view Reconstruction
We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their latent 3D shapes solely using recognition. We cal...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2014
|
| Online Access: | http://hdl.handle.net/1721.1/91001 https://orcid.org/0000-0001-9020-9593 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1826213559341678592 |
|---|---|
| author | Xiao, Jianxiong Torralba, Antonio Owens, Andrew Hale Freeman, William T. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Xiao, Jianxiong Torralba, Antonio Owens, Andrew Hale Freeman, William T. |
| author_sort | Xiao, Jianxiong |
| collection | MIT |
| description | We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their latent 3D shapes solely using recognition. We call these patches shape anchors, and we use them as the basis of a multi-view reconstruction system that transfers dense, complex geometry between scenes. We "anchor" our 3D interpretation from these patches, using them to predict geometry for parts of the scene that are relatively ambiguous. The resulting algorithm produces dense reconstructions from stereo point clouds that are sparse and noisy, and we demonstrate it on a challenging dataset of real-world, indoor scenes. |
| first_indexed | 2024-09-23T15:51:10Z |
| format | Article |
| id | mit-1721.1/91001 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:51:10Z |
| publishDate | 2014 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/910012022-10-02T04:32:52Z Shape Anchors for Data-Driven Multi-view Reconstruction Xiao, Jianxiong Torralba, Antonio Owens, Andrew Hale Freeman, William T. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Owens, Andrew Hale Torralba, Antonio Freeman, William T. We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their latent 3D shapes solely using recognition. We call these patches shape anchors, and we use them as the basis of a multi-view reconstruction system that transfers dense, complex geometry between scenes. We "anchor" our 3D interpretation from these patches, using them to predict geometry for parts of the scene that are relatively ambiguous. The resulting algorithm produces dense reconstructions from stereo point clouds that are sparse and noisy, and we demonstrate it on a challenging dataset of real-world, indoor scenes. American Society for Engineering Education. National Defense Science and Engineering Graduate Fellowship United States. Office of Naval Research. Multidisciplinary University Research Initiative (N000141010933) National Science Foundation (U.S.) (Grant CGV-1212928) 2014-10-20T18:14:37Z 2014-10-20T18:14:37Z 2013-12 Article http://purl.org/eprint/type/ConferencePaper 978-1-4799-2840-8 1550-5499 http://hdl.handle.net/1721.1/91001 Owens, Andrew, Jianxiong Xiao, Antonio Torralba, and William Freeman. “Shape Anchors for Data-Driven Multi-View Reconstruction.” 2013 IEEE International Conference on Computer Vision (December 2013). https://orcid.org/0000-0001-9020-9593 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/10.1109/ICCV.2013.461 Proceedings of the 2013 IEEE International Conference on Computer Vision Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Xiao, Jianxiong Torralba, Antonio Owens, Andrew Hale Freeman, William T. Shape Anchors for Data-Driven Multi-view Reconstruction |
| title | Shape Anchors for Data-Driven Multi-view Reconstruction |
| title_full | Shape Anchors for Data-Driven Multi-view Reconstruction |
| title_fullStr | Shape Anchors for Data-Driven Multi-view Reconstruction |
| title_full_unstemmed | Shape Anchors for Data-Driven Multi-view Reconstruction |
| title_short | Shape Anchors for Data-Driven Multi-view Reconstruction |
| title_sort | shape anchors for data driven multi view reconstruction |
| url | http://hdl.handle.net/1721.1/91001 https://orcid.org/0000-0001-9020-9593 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT xiaojianxiong shapeanchorsfordatadrivenmultiviewreconstruction AT torralbaantonio shapeanchorsfordatadrivenmultiviewreconstruction AT owensandrewhale shapeanchorsfordatadrivenmultiviewreconstruction AT freemanwilliamt shapeanchorsfordatadrivenmultiviewreconstruction |