SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Stereo Matching with Transparency and Matting
International Journal of Computer Vision - 1998 Marr Prize
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Motion and Appearance of Specularities in Image Sequences
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Bayesian Estimation of Layers from Multiple Images
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Skin and Bones: Multi-layer, Locally Affine, Optical Flow and Regularization with Transparency
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
A Space-Sweep Approach to True Multi-Image Matching
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
ACM SIGGRAPH 2003 Papers
Extracting View-Dependent Depth Maps from a Collection of Images
International Journal of Computer Vision - Special Issue on Research at Microsoft Corporation
High-quality video view interpolation using a layered representation
ACM SIGGRAPH 2004 Papers
Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance
International Journal of Computer Vision
Boundary matting for view synthesis
Computer Vision and Image Understanding
Stereo for Image-Based Rendering using Image Over-Segmentation
International Journal of Computer Vision
Foundations and Trends® in Computer Graphics and Vision
Blind separation of convolutive image mixtures
Neurocomputing
Hi-index | 0.00 |
In this paper, we address the stereo matching problem in the presence of reflections and translucency, where image formation can be modeled as the additive superposition of layers at different depth. The presence of such effects violates the Lambertian assumption underlying traditional stereo vision algorithms, making it impossible to recover component depths using direct color matching based methods. We develop several techniques to estimate both depths and colors of the component layers. Depth hypotheses are enumerated in pairs, one from each layer, in a nested plane sweep. For each pair of depth hypotheses, we compute a componentcolor-independentmatching error per pixel, using a spatialtemporal-differencing technique. We then use graph cut optimization to solve for the depths of both layers. This is followed by an iterative color update algorithm whose convergence is proven in our paper. We show convincing results of depth and color estimates for both synthetic and real image sequences.