Dynamically reparameterized light fields
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bi-Layer Segmentation of Binocular Stereo Video
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Multilevel Banded Graph Cuts Method for Fast Image Segmentation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Natural video matting using camera arrays
ACM SIGGRAPH 2006 Papers
Bilayer Segmentation of Live Video
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
A Bayesian Framework for Simultaneous Matting and 3D Reconstruction
3DIM '07 Proceedings of the Sixth International Conference on 3-D Digital Imaging and Modeling
Live Video Segmentation in Dynamic Backgrounds Using Thermal Vision
PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
IEEE Transactions on Circuits and Systems for Video Technology
Joint 3D-reconstruction and background separation in multiple views using graph cuts
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Survey of image-based representations and compression techniques
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
This paper presents a method that jointly performs synthesis and object segmentation of free-viewpoint video using multiview video as the input. This method is designed to achieve robust segmentation from online video input without per-frame user interaction and precomputations. This method shares a calculation process between the synthesis and segmentation steps; the matching costs calculated through the synthesis step are adaptively fused with other cues depending on the reliability in the segmentation step. Since the segmentation is performed for arbitrary viewpoints directly, the extracted object can be superimposed onto another 3D scene with geometric consistency. We can observe that the object and new background move naturally along with the viewpoint change as if they existed together in the same space. In the experiments, our method can process online video input captured by a 25-camera array and show the result image at 4.55 fps.