Japanese / English

Detail of Publication

Text Language English
Authors Fairuz Safwan Mahad, Masakazu Iwamura, and Koichi Kise
Title Learning multi-level features for improved 3D reconstruction
Journal IEICE Transactions on Information and Systems
Vol. E106-D
No. 3
Pages pp.381-390
Number of Pages 9 pages
Publisher IEICE
Reviewed or not Reviewed
Month & Year March 2023
Abstract 3D reconstruction methods using neural networks are popular and have been studied extensively. However, the resulting models typically lack detail, reducing the quality of the 3D reconstruction. This is because the network is not designed to capture the fine details of the object. Therefore, in this paper, we propose two networks designed to capture both the coarse and fine details of the object to improve the reconstruction of the detailed parts of the object. To accomplish this, we design two networks. The first network uses a multi-scale architecture with skip connections to associate and merge features from other levels. For the second network, we design a multi-branch deep generative network that separately learns the local features, generic features, and the intermediate features through three different tailored components. In both network architectures, the principle entails allowing the network to learn features at different levels that can reconstruct the fine parts and the overall shape of the reconstructed 3D model. We show that both of our methods outperformed state-of-the-art approaches.
DOI 10.1587/transinf.2020ZDL0001
Back to list