Abstract | ||
---|---|---|
We present an algorithm for transferring physical attributes between webpages and 3D shapes. We crawl product catalogues and other webpages with structured metadata containing physical attributes such as dimensions and weights. Then we transfer physical attributes between shapes and real-world objects using a joint embedding of images and 3D shapes and a view-based weighting and aspect ratio filtering scheme for instance-level linking of 3D models and real-world counterpart objects. We evaluate our approach on a large-scale dataset of unscaled 3D models, and show that we outperform prior work on rescaling 3D models that considers only category-level size priors. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/3DV.2017.00078 | 2017 International Conference on 3D Vision (3DV) |
Keywords | Field | DocType |
3D-models,metric-size-prediction,cross-modal-attribute-transfer | Metadata,Weighting,Embedding,Web page,Pattern recognition,Computer science,3d shapes,Filter (signal processing),Artificial intelligence,Prior probability,Modal | Conference |
ISSN | ISBN | Citations |
2378-3826 | 978-1-5386-2611-5 | 2 |
PageRank | References | Authors |
0.39 | 14 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin Shao | 1 | 12 | 3.33 |
Angel Chang | 2 | 1340 | 58.19 |
Hao Su | 3 | 7343 | 302.07 |
Manolis Savva | 4 | 578 | 25.50 |
Leonidas J. Guibas | 5 | 13084 | 1262.73 |