Self-Occlusions and Disocclusions in Causal Video Object Segmentation
KAUST DepartmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
Visual Computing Center (VCC)
Online Publication Date2016-02-19
Print Publication Date2015-12
Permanent link to this recordhttp://hdl.handle.net/10754/621290
MetadataShow full item record
AbstractWe propose a method to detect disocclusion in video sequences of three-dimensional scenes and to partition the disoccluded regions into objects, defined by coherent deformation corresponding to surfaces in the scene. Our method infers deformation fields that are piecewise smooth by construction without the need for an explicit regularizer and the associated choice of weight. It then partitions the disoccluded region and groups its components with objects by leveraging on the complementarity of motion and appearance cues: Where appearance changes within an object, motion can usually be reliably inferred and used for grouping. Where appearance is close to constant, it can be used for grouping directly. We integrate both cues in an energy minimization framework, incorporate prior assumptions explicitly into the energy, and propose a numerical scheme. © 2015 IEEE.
CitationYang Y, Sundaramoorthi G, Soatto S (2015) Self-Occlusions and Disocclusions in Causal Video Object Segmentation. 2015 IEEE International Conference on Computer Vision (ICCV). Available: http://dx.doi.org/10.1109/ICCV.2015.501.
Conference/Event name15th IEEE International Conference on Computer Vision, ICCV 2015