3D shape attributes
In this paper we investigate 3D attributes as a means to understand the shape of an object in a single image. To this end, we make a number of contributions: (i) we introduce and define a set of 3D Shape attributes, including planarity, symmetry and occupied space; (ii) we show that such properties...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| _version_ | 1826265656351260672 |
|---|---|
| author | Fouhey, D Gupta, A Zisserman, A |
| author_facet | Fouhey, D Gupta, A Zisserman, A |
| author_sort | Fouhey, D |
| collection | OXFORD |
| description | In this paper we investigate 3D attributes as a means to understand the shape of an object in a single image. To this end, we make a number of contributions: (i) we introduce and define a set of 3D Shape attributes, including planarity, symmetry and occupied space; (ii) we show that such properties can be successfully inferred from a single image using a Convolutional Neural Network (CNN); (iii) we introduce a 143K image dataset of sculptures with 2197 works over 242 artists for training and evaluating the CNN; (iv) we show that the 3D attributes trained on this dataset generalize to images of other (non-sculpture) object classes; and furthermore (v) we show that the CNN also provides a shape embedding that can be used to match previously unseen sculptures largely independent of viewpoint. |
| first_indexed | 2024-03-06T20:27:05Z |
| format | Conference item |
| id | oxford-uuid:2fc1a3a9-44ed-4174-815a-cfad971220ad |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:27:05Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:2fc1a3a9-44ed-4174-815a-cfad971220ad2022-03-26T12:57:19Z3D shape attributesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:2fc1a3a9-44ed-4174-815a-cfad971220adSymplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2010Fouhey, DGupta, AZisserman, AIn this paper we investigate 3D attributes as a means to understand the shape of an object in a single image. To this end, we make a number of contributions: (i) we introduce and define a set of 3D Shape attributes, including planarity, symmetry and occupied space; (ii) we show that such properties can be successfully inferred from a single image using a Convolutional Neural Network (CNN); (iii) we introduce a 143K image dataset of sculptures with 2197 works over 242 artists for training and evaluating the CNN; (iv) we show that the 3D attributes trained on this dataset generalize to images of other (non-sculpture) object classes; and furthermore (v) we show that the CNN also provides a shape embedding that can be used to match previously unseen sculptures largely independent of viewpoint. |
| spellingShingle | Fouhey, D Gupta, A Zisserman, A 3D shape attributes |
| title | 3D shape attributes |
| title_full | 3D shape attributes |
| title_fullStr | 3D shape attributes |
| title_full_unstemmed | 3D shape attributes |
| title_short | 3D shape attributes |
| title_sort | 3d shape attributes |
| work_keys_str_mv | AT fouheyd 3dshapeattributes AT guptaa 3dshapeattributes AT zissermana 3dshapeattributes |