TriangleFlow: optical flow with triangulation-based higher-order likelihoods
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Topology-preserving registration: a solution via graph cuts
IWCIA'11 Proceedings of the 14th international conference on Combinatorial image analysis
A fast solver for truncated-convex priors: quantized-convex split moves
EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
A Spatial Regularization Approach for Vector Quantization
Journal of Mathematical Imaging and Vision
Automated cephalometric landmark localization using sparse shape and appearance models
MLMI'11 Proceedings of the Second international conference on Machine learning in medical imaging
Parallel and distributed vision algorithms using dual decomposition
Computer Vision and Image Understanding
Generalized roof duality and bisubmodular functions
Discrete Applied Mathematics
Over-Parameterized optical flow using a stereoscopic constraint
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
Minimizing Energies with Hierarchical Costs
International Journal of Computer Vision
Discrete Applied Mathematics
Fast fusion moves for multi-model estimation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Soft inextensibility constraints for template-free non-rigid reconstruction
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Dynamic programming for approximate expansion algorithm
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Multiple view object cosegmentation using appearance and stereo cues
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Contraction moves for geometric model fitting
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Reliable assessment of perfusivity and diffusivity from diffusion imaging of the body
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Tighter relaxations for higher-order models based on generalized roof duality
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Review article: Multilabel partition moves for MRF optimization
Image and Vision Computing
Estimating shadows with the bright channel cue
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Adaptive large window correlation for optical flow estimation with discrete optimization
Image and Vision Computing
Computer Vision and Image Understanding
International Journal of Computer Vision
Hi-index | 0.14 |
The efficient application of graph cuts to Markov Random Fields (MRFs) with multiple discrete or continuous labels remains an open question. In this paper, we demonstrate one possible way of achieving this by using graph cuts to combine pairs of suboptimal labelings or solutions. We call this combination process the fusion move. By employing recently developed graph-cut-based algorithms (so-called QPBO-graph cut), the fusion move can efficiently combine two proposal labelings in a theoretically sound way, which is in practice often globally optimal. We demonstrate that fusion moves generalize many previous graph-cut approaches, which allows them to be used as building blocks within a broader variety of optimization schemes than were considered before. In particular, we propose new optimization schemes for computer vision MRFs with applications to image restoration, stereo, and optical flow, among others. Within these schemes the fusion moves are used 1) for the parallelization of MRF optimization into several threads, 2) for fast MRF optimization by combining cheap-to-compute solutions, and 3) for the optimization of highly nonconvex continuous-labeled MRFs with 2D labels. Our final example is a nonvision MRF concerned with cartographic label placement, where fusion moves can be used to improve the performance of a standard inference method (loopy belief propagation).