Pop-up light field: An interactive image-based modeling and rendering system
ACM Transactions on Graphics (TOG)
Adaptive Region-Based Video Registration
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Motion Layer Extraction in the Presence of Occlusion Using Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking based motion segmentation under relaxed statistical assumptions
Computer Vision and Image Understanding
A Unified Algebraic Approach to 2-D and 3-D Motion Segmentation and Estimation
Journal of Mathematical Imaging and Vision
Occlusion Boundaries from Motion: Low-Level Detection and Mid-Level Reasoning
International Journal of Computer Vision
Local detection of occlusion boundaries in video
Image and Vision Computing
Analysis of Rain and Snow in Frequency Space
International Journal of Computer Vision
Robust subspace clustering by combined use of kNND metric and SVD algorithm
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Motion layer extraction in the presence of occlusion using graph cut
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Background updating for visual surveillance
ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Multi-layer spectral clustering for video segmentation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
| Hi-index | 0.00 |
Representing images with layers has many important applications,such as video compression, motion analysis, and3D scene analysis. This paper presents a robust subspaceapproach to reliably extracting layers from images by takingadvantages of the fact that homographies induced byplanar patches in the scene form a low dimensional linearsubspace. Such subspace provides not only a featurespace where layers in the image domain are mapped ontodenser and better-defined clusters, but also a constraint fordetecting outliers in the local measurements, thus makingthe algorithm robust to outliers. By enforcing the subspaceconstraint, spatial and temporal redundancy from multipleframes are simultaneously utilized, and noise can be effectivelyreduced. Good layer descriptions are shown to beextracted in the experimental results.