Affiliation:
1. Industrial Systems Institute, Athena Research Center, Stadiou, Platani, Achaia, Greece
2. Department of Electrical & Computer Engineering, University of Patras, Panepistimioupoli, Rio, Achaia, Greece
Abstract
Nowadays, three-dimensional (3D) meshes are widely used in various applications in different areas (e.g., industry, education, entertainment and safety). The 3D models are captured with multiple RGB-D sensors, and the sampled geometric manifolds are processed, compressed, simplified, stored, and transmitted to be reconstructed in a virtual space. These low-level processing applications require the accurate representation of the 3D models that can be achieved through saliency estimation mechanisms that identify specific areas of the 3D model representing surface patches of importance. Therefore, saliency maps guide the selection of feature locations facilitating the prioritization of 3D manifold segments and attributing to vertices more bits during compression or lower decimation probability during simplification, since compression and simplification are counterparts of the same process. In this work, we present a novel deep saliency mapping approach applied to 3D meshes, emphasizing decreasing the execution time of the saliency map estimation, especially when compared with the corresponding time by other relevant approaches. Our method utilizes baseline 3D importance maps to train convolutional neural networks. Furthermore, we present applications that utilize the extracted saliency, namely feature-aware multiscale compression and simplification frameworks.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture
Reference40 articles.
1. An Integrated Platform for Live 3D Human Reconstruction and Motion Capturing
2. Real-time, full 3-D reconstruction of moving foreground objects from multiple consumer depth cameras;Alexiadis Dimitrios S.;IEEE Trans. Multimedia,2012
3. Dimitrios S. Alexiadis, Dimitrios Zarpalas, and Petros Daras. 2013. Real-time, realistic full-body 3D reconstruction and texture mapping from multiple kinects. In Proceedings of the Image, Video, and Multidimensional Signal Processing Workshop (IVMSP’13). IEEE, 1–4.
4. Guangming An, Taichi Watanabe, and Masanori Kakimoto. 2016. Mesh simplification using hybrid saliency. In Proceedings of the International Conference on Cyberworlds (CW’16). IEEE, 231–234.
5. Adaptive representation of dynamic 3D meshes for low-latency applications
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献