Bilateral Space Video Segmentation
Authors:
- Nicolas MarkiNMNicolas Marki
- Federico PerazziFPFederico Perazzi
- Oliver WangOWOliver Wang
- Alexander Sorkine-HornungASAlexander Sorkine-Hornung
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 743-751
Abstract
In this work, we propose a novel approach to video segmentation that operates in bilateral space. We design a new energy on the vertices of a regularly sampled spatiotemporal bilateral grid, which can be solved efficiently using a standard graph cut label assignment. Using a bilateral formulation, the energy that we minimize implicitly approximates long-range, spatio-temporal connections between pixels while still containing only a small number of variables and only local graph edges. We compare to a number of recent methods, and show that our approach achieves state-of-the-art results on multiple benchmarks in a fraction of the runtime. Furthermore, our method scales linearly with image size, allowing for interactive feedback on real-world high resolution video.Keywords
This publication has 33 references indexed in Scilit:
- SeamSeg: Video Object Segmentation Using Patch Seams2014
- Video Object Segmentation by Non-Local Consensus voting2014
- Interactive Segmentation of High-Resolution Video Content Using Temporally Coherent Superpixels and Graph Cut2014
- Discontinuity-aware video object cutoutACM Transactions on Graphics, 2012
- Practical temporal consistency for image-based graphics applicationsACM Transactions on Graphics, 2012
- Gaussian KD-trees for fast high-dimensional filteringACM Transactions on Graphics, 2009
- Video SnapCutACM Transactions on Graphics, 2009
- Video object cut and pasteACM Transactions on Graphics, 2005
- Interactive video cutoutACM Transactions on Graphics, 2005
- "GrabCut"2004