A new approach to the maximum-flow problem
Journal of the ACM (JACM)
On the parallel implementation of Goldberg's maximum flow algorithm
SPAA '92 Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
What Energy Functions Can Be Minimizedvia Graph Cuts?
IEEE Transactions on Pattern Analysis and Machine Intelligence
An O (n log n) algorithm for maximum st-flow in a directed planar graph
SODA '06 Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Convergent Tree-Reweighted Message Passing for Energy Minimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic Graph Cuts for Efficient Inference in Markov Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
A comparative study of energy minimization methods for markov random fields
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Parallel and distributed vision algorithms using dual decomposition
Computer Vision and Image Understanding
Hi-index | 0.00 |
Many vision problems map to the minimization of an energy function over a discrete MRF Fast performance is needed if the energy minimization is one step in a control loop In this paper, we present the incremental α-expansion algorithm for high-performance multilabel MRF optimization on the GPU Our algorithm utilizes the grid structure of the MRFs for good parallelism on the GPU We improve the basic push-relabel implementation of graph cuts using the atomic operations of the GPU and by processing blocks stochastically We also reuse the flow using reparametrization of the graph from cycle to cycle and iteration to iteration for fast performance We show results on various vision problems on standard datasets Our approach takes 950 milliseconds on the GPU for stereo correspondence on Tsukuba image with 16 labels compared to 5.4 seconds on the CPU.