What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
N. Mayer, E. Ilg, P. Fischer, C. Hazirbas, D. Cremers, A. Dosovitskiy, and T. Brox
IJCV, January 2018
bib | arXiv ]
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
T. Meinhardt, M. Möller, C. Hazirbas, and D. Cremers
ICCV, October 2017
bib | arXiv | source ]
Image-based localization using LSTMs for structured feature correlation
F. Walch, C. Hazirbas, L. Leal-Taixé, T. Sattler, S. Hilsenbeck, and D. Cremers
ICCV, October 2017
bib | arXiv | source ]
Deep Depth From Focus
C. Hazirbas, L. Leal-Taixé, and D. Cremers
ArXiv, April 2017
bib | arXiv | source ]
FuseNet:Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture
C. Hazirbas, L. Ma, C. Domokos, and D. Cremers
ACCV, November 2016
bib | doi | source ]
FlowNet: Learning Optical Flow with Convolutional Networks
A. Dosovitskiy, P. Fischer, E. Ilg, P. Haeusser, C. Hazirbas, V. Golkov, P. van der Smagt, D. Cremers, and T. Brox
ICCV, December 2015
bib | arXiv | doi ]
CAPTCHA Recognition with Active Deep Learning
F. Stark, C. Hazirbas, R. Triebel, and D. Cremers
GCPRW, October 2015
bib | source ]
Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation
C. Hazirbas, J. Diebold, and D. Cremers
SSVM, June 2015 Oral Presentation
bib | doi | source ]
Interactive Multi-label Segmentation of RGB-D Images
J. Diebold, N. Demmel, C. Hazirbas, M. Möller, and D. Cremers
SSVM, June 2015
bib | doi | source ]
Feature Selection and Learning for Semantic Segmentation
C. Hazirbas
Master's thesis, Technical University Munich, Germany, June 2014
bib ]