• Publications
  • Influence
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
FlowNet: Learning Optical Flow with Convolutional Networks
TLDR
This paper constructs CNNs which are capable of solving the optical flow estimation problem as a supervised learning task, and proposes and compares two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
  • N. Mayer, Eddy Ilg, +4 authors T. Brox
  • Computer Science, Mathematics
    IEEE Conference on Computer Vision and Pattern…
  • 7 December 2015
TLDR
This paper proposes three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks and presents a convolutional network for real-time disparity estimation that provides state-of-the-art results.
Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
TLDR
While features learned with this approach cannot compete with class specific features from supervised training on a classification task, it is shown that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.
Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT
TLDR
This paper compares features from various layers of convolutional neural nets to standard SIFT descriptors and Surprisingly, convolutionAL neural networks clearly outperform SIFT on descriptor matching.
A benchmark for comparison of dental radiography analysis algorithms
TLDR
Based on the quantitative evaluation results, it is believed automatic dental radiography analysis is still a challenging and unsolved problem and the datasets and the evaluation software are made available to the research community, further encouraging future developments in this field.
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
  • N. Mayer, Eddy Ilg, +4 authors T. Brox
  • Computer Science, Mathematics
    International Journal of Computer Vision
  • 19 January 2018
TLDR
This paper promotes the use of synthetically generated data for the purpose of training deep networks on visual recognition tasks and suggests multiple ways to generate such data and evaluates the influence of dataset properties on the performance and generalization properties of the resulting networks.
Image Orientation Estimation with Convolutional Networks
TLDR
It is demonstrated that a convolutional network can learn subtle features to predict the canonical orientation of images, and this approach runs in real-time and can be applied also to live video streams.
A practical guide to the use of consumer-level digital still cameras for precise stereogrammetric in situ assessments in aquatic environments
Scientists planning to use underwater stereoscopic image technologies are often faced with numerous problems during the methodological implementations: commercial equipment is too expensive; the
...
1
2
...