• Publications
  • Influence
U-Net: Convolutional Networks for Biomedical Image Segmentation
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. Expand
FlowNet: Learning Optical Flow with Convolutional Networks
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. Expand
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training. Expand
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
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. Expand
Striving for Simplicity: The All Convolutional Net
It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Expand
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
The concept of end-to-end learning of optical flow is advanced and it work really well, and faster variants that allow optical flow computation at up to 140fps with accuracy matching the original FlowNet are presented. Expand
High Accuracy Optical Flow Estimation Based on a Theory for Warping
By proving that this scheme implements a coarse-to-fine warping strategy, this work gives a theoretical foundation for warping which has been used on a mainly experimental basis so far and demonstrates its excellent robustness under noise. Expand
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation
  • T. Brox, Jitendra Malik
  • Mathematics, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 March 2011
A way to approach the problem of dense optical flow estimation by integrating rich descriptors into the variational optical flow setting, while reaching out to new domains of motion analysis where the requirement of dense sampling in time is no longer satisfied is presented. Expand
Object Segmentation by Long Term Analysis of Point Trajectories
This paper presents a method that uses long term point trajectories based on dense optical flow to define pair-wise distances between these trajectories, which results in temporally consistent segmentations of moving objects in a video shot. Expand
Learning to Estimate 3D Hand Pose from Single RGB Images
A deep network is proposed that learns a network-implicit 3D articulation prior that yields good estimates of the 3D pose from regular RGB images, and a large scale 3D hand pose dataset based on synthetic hand models is introduced. Expand