A fully-connected layered model of foreground and background flow

2013

Conference Paper

ps


Layered models allow scene segmentation and motion estimation to be formulated together and to inform one another. Traditional layered motion methods, however, employ fairly weak models of scene structure, relying on locally connected Ising/Potts models which have limited ability to capture long-range correlations in natural scenes. To address this, we formulate a fully-connected layered model that enables global reasoning about the complicated segmentations of real objects. Optimization with fully-connected graphical models is challenging, and our inference algorithm leverages recent work on efficient mean field updates for fully-connected conditional random fields. These methods can be implemented efficiently using high-dimensional Gaussian filtering. We combine these ideas with a layered flow model, and find that the long-range connections greatly improve segmentation into figure-ground layers when compared with locally connected MRF models. Experiments on several benchmark datasets show that the method can recover fine structures and large occlusion regions, with good flow accuracy and much lower computational cost than previous locally-connected layered models.

Author(s): Deqing Sun and Jonas Wulff and Erik Sudderth and Hanspeter Pfister and Michael Black
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition, (CVPR 2013)
Pages: 2451--2458
Year: 2013
Month: June

Department(s): Perceiving Systems
Research Project(s): Layers, Time and Segmentation
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: Portland, OR

Links: pdf
Supplemental Material

BibTex

@inproceedings{Sun:CVPR:2013,
  title = {A fully-connected layered model of foreground and background flow},
  author = {Sun, Deqing and Wulff, Jonas and Sudderth, Erik and Pfister, Hanspeter and Black, Michael},
  booktitle = {IEEE Conf. on Computer Vision and Pattern Recognition, (CVPR 2013)},
  pages = {2451--2458},
  address = {Portland, OR},
  month = jun,
  year = {2013},
  month_numeric = {6}
}