Abstract | ||
---|---|---|
This work developed a robust 2D to 3D digital video conversion technique that allows traditional 2D video content to be displayed as 3D video. The main principle of this work is to infer an accurate depth map for each frame from the 2D video sequence as with the inter-frame consistence. First, we infer three depth maps for each frame: initial block-wise depth map, initial pixel-wise depth map, and region-wise propagated depth map. Then, Kalman filter is introduced to fuse three depth maps to a final depth map. Once the depth map of the 2D video is obtained, we can generate the left and right images with it through DIBR algorithm, and display it on 3D stereoscopic display. |
Year | DOI | Venue |
---|---|---|
2014 | 10.3233/978-1-61499-484-8-1175 | Frontiers in Artificial Intelligence and Applications |
Keywords | Field | DocType |
Single-view video,depth estimation,depth propagation,optical flow,stereoscopic display | Computer vision,Computer graphics (images),Inference,Computer science,2D to 3D conversion,Real-time computing,Artificial intelligence | Conference |
Volume | ISSN | Citations |
274 | 0922-6389 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tien-Ying Kuo | 1 | 148 | 19.24 |
Cheng-Hong Hsieh | 2 | 0 | 0.34 |
Kuan-Hung Wan | 3 | 0 | 0.34 |
Yan-Jhu Chen | 4 | 0 | 0.34 |