- Autor
- Knöbelreiter, Patrick
- Reinbacher, Christian
- Shekhovtsov, Alexander
- Pock, Thomas
- TitelEnd-to-End Training of Hybrid CNN-CRF Models for Stereo
- Datei
- Persistent Identifier
- Erschienen inarXiv.org e-Print archive
- Erscheinungsjahr2016
- LicenceCC-BY
- Download Statistik1644
- Peer ReviewJa
- AbstractWe propose a novel method for stereo estimation, combining advantages of convolutional neural networks (CNNs) and optimization-based approaches. The optimization, posed as a conditional random field (CRF), takes local matching costs and consistency-enforcing (smoothness) costs as inputs, both estimated by CNN blocks. To perform the inference in the CRF we use an approach based on linear programming relaxation with a fixed number of iterations. We address the challenging problem of training this hybrid model end-to-end. We show that in the discriminative formulation (structured support vector machine) the training is practically feasible. The trained hybrid model with shallow CNNs is comparable to state-of-the-art deep models in both time and performance. The optimization part efficiently replaces sophisticated and not jointly trainable (but commonly applied) post-processing steps by a trainable, well-understood model.
[9.24 MB]