文献の詳細
| 論文の言語 | 英語 |
|---|---|
| 著者 | Fairuz Safwan Mahad, Masakazu Iwamura and Koichi Kise |
| 論文名 | Leveraging Pyramidal Feature Hierarchy for 3D Reconstruction |
| 論文誌名 | Proc. International Workshop on Frontiers of Computer Vision (IW-FCV) |
| ページ | pp.347-362 |
| 発表場所 | Ibusuki, Japan |
| 査読の有無 | 有 |
| 発表の種類 | 口頭発表 |
| 年月 | 2020年2月 |
| 要約 | 3D reconstruction methods with neural networks has been on a rising trend and extensive research has been done. However, they do not pay particular attention to reconstructing the detailed parts of the objects. Although the reconstructed 3D models often look complete generally, close-up observations reveal that most of them lose out on the detailed parts, which reduces the quality of the 3D model. We observe that especially fine parts of the object either fail to be reconstructed or are less dense and incomplete. This happens because the network is not designed to capture the fine details of the object. Therefore, in this paper, we propose a network which is designed to capture both the coarse and fine details of the object in an effort to improve the reconstruction of the fine parts of the object. In order to do so, we design a multi-branch deep generative network which learns the local features, generic features and also intermediate features. Utilizing these features allows the network to learn features at different levels which are able to reconstruct the fine parts as well as the overall shape of the reconstructed 3D model. We show that our method outperformed the state-of-the-art. |
| DOI | 10.1007/978-981-15-4818-5_26 |
- 次のファイルが利用可能です．
- BibTeX用エントリー
@InProceedings{Mahad2020, author = {Fairuz Safwan Mahad and Masakazu Iwamura and Koichi Kise}, title = {Leveraging Pyramidal Feature Hierarchy for 3D Reconstruction}, booktitle = {Proc. International Workshop on Frontiers of Computer Vision (IW-FCV)}, year = 2020, month = feb, pages = {347--362}, DOI = {10.1007/978-981-15-4818-5_26}, location = {Ibusuki, Japan} }