Abstract | ||
---|---|---|
Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach for 3-D scene reconstruction. In this paper, we explore an improved stereo matching network, SLED-Net, in which a Single Long Encoder-Decoder is proposed to replace the stacked hourglass network in PSM-Net for better contextual information learning. We compare SLED-Net to state-of-the-art methods recently published, and demonstrate its superior performance on Scene Flow and KITTI2015 test sets. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/VR.2019.8797778 | 2019 26TH IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES (VR) |
Keywords | Field | DocType |
Computing methodologies-Scene understanding, Computing methodologies-Reconstruction, Computing methodologies-Mixed/augmented reality | Stereo matching,Computer vision,Contextual information,Pattern recognition,Computer science,Image processing,Augmented reality,Artificial intelligence | Journal |
Volume | Citations | PageRank |
abs/1902.06255 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guangyu Nie | 1 | 10 | 3.21 |
Yun Liu | 2 | 0 | 0.34 |
Cong Wang | 3 | 0 | 1.01 |
Yue Liu | 4 | 100 | 23.05 |
Yongtian Wang | 5 | 456 | 73.00 |