Caner Hazirbas

Caner Hazirbas

Auto-generated profile, based on publicly available information

Caner Hazirbas

Technical University of Munich

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2015
Verified
Conference Paper
Closed access
ADAlexey Dosovitskiy
Alexey Dosovitskiy
PFPhilipp Fischer
Philipp Fischer
EIEddy Ilg
Eddy Ilg
PHPhilip Hausser
Philip Hausser
CHCaner Hazirbas
Caner Hazirbas
TBThomas Brox
Thomas Brox
Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not been among the tasks CNNs succeeded at. In this paper we construct CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations. Since existing ground truth data sets are not sufficiently large to train a CNN, we generate a large synthetic Flying Chairs dataset. We show that networks trained on this unrealistic data still generalize very well to existing datasets such as Sintel and KITTI, achieving competitive accuracy at frame rates of 5 to 10 fps.

10 March 2017
Verified
Book Chapter
Closed access
PDF file
CHCaner Hazirbas
Caner Hazirbas
LMLingni Ma
Lingni Ma
CDCsaba Domokos
Csaba Domokos
DCDaniel Cremers
Daniel Cremers

1 October 2017
Verified
Conference Paper
Closed access
FWF. Walch
F. Walch
CHC. Hazirbas
C. Hazirbas
LLL. Leal-Taixe
L. Leal-Taixe
TST. Sattler
T. Sattler
SHS. Hilsenbeck
S. Hilsenbeck
DCD. Cremers
D. Cremers
In this work we propose a new CNN+LSTM architecture for camera pose regression for indoor and outdoor scenes. CNNs allow us to learn suitable feature representations for localization that are robust against motion blur and illumination changes. We make use of LSTM units on the CNN output, which play the role of a structured dimensionality reduction on the feature vector, leading to drastic improvements in localization performance. We provide extensive quantitative comparison of CNN-based and SIFT-based localization methods, showing the weaknesses and strengths of each. Furthermore, we present a new large-scale indoor dataset with accurate ground truth from a laser scanner. Experimental results on both indoor and outdoor public datasets show our method outperforms existing deep architectures, and can localize images in hard conditions, e.g., in the presence of mostly textureless surfaces, where classic SIFT-based methods fail.

1 October 2017
Verified
Conference Paper
Closed access
TMTim Meinhardt
Tim Meinhardt
MMMichael Moeller
Michael Moeller
CHCaner Hazirbas
Caner Hazirbas
DCDaniel Cremers
Daniel Cremers
While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks. A remaining drawback of deep learning approaches is their requirement for an expensive retraining whenever the specific problem, the noise level, noise type, or desired measure of fidelity changes. On the contrary, variational methods have a plug-and-play nature as they usually consist of separate data fidelity and regularization terms. In this paper we study the possibility of replacing the proximal operator of the regularization used in many convex energy minimization algorithms by a denoising neural network. The latter therefore serves as an implicit natural image prior, while the data term can still be chosen independently. Using a fixed denoising neural network in exemplary problems of image deconvolution with different blur kernels and image demosaicking, we obtain state-of-the-art reconstruction results. These indicate the high generalizability of our approach and a reduction of the need for problem-specific training. Additionally, we discuss novel results on the analysis of possible optimization algorithms to incorporate the network into, as well as the choices of algorithm parameters and their relation to the noise level the neural network is trained on.

3 December 2021 in IEEE Transactions on Biometrics, Behavior, and Identity Science
Verified
Journal Article
Closed access
CHCaner Hazirbas
Caner Hazirbas
JBJoanna Bitton
Joanna Bitton
BDBrian Dolhansky
Brian Dolhansky
JPJacqueline Pan
Jacqueline Pan
AGAlbert Gordo
Albert Gordo
CFCristian Canton Ferrer
Cristian Canton Ferrer
This paper introduces a novel dataset to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of age, genders, apparent skin tones and ambient lighting conditions. Our dataset is composed of 3,011 subjects and contains over 45,000 videos, with an average of 15 videos per person. The videos were recorded in multiple U.S. states with a diverse set of adults in various age, gender and apparent skin tone groups. A key feature is that each subject agreed to participate for their likenesses to be used. Additionally, our age and gender annotations are provided by the subjects themselves. A group of trained annotators labeled the subjects’ apparent skin tone using the Fitzpatrick skin type scale. Moreover, annotations for videos recorded in low ambient lighting are also provided. As an application to measure robustness of predictions across certain attributes, we provide a comprehensive study on the top five winners of the DeepFake Detection Challenge (DFDC). Experimental evaluation shows that the winning models are less performant on some specific groups of people, such as subjects with darker skin tones and thus may not generalize to all people. In addition, we also evaluate the state-of-the-art apparent age and gender classification methods. Our experiments provides a thorough analysis on these models in terms of fair treatment of people from various backgrounds.

29 May 2019
Verified
Book Chapter
Closed access
PDF file
CHCaner Hazirbas
Caner Hazirbas
SSSebastian Georg Soyer
Sebastian Georg Soyer
MSMaximilian Christian Staab
Maximilian Christian Staab
LLLaura Leal-Taixé
Laura Leal-Taixé
DCDaniel Cremers
Daniel Cremers