• Publications
  • Influence
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, T. Brox
  • Computer Science
    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.
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
TLDR
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.
DeMoN: Depth and Motion Network for Learning Monocular Stereo
TLDR
This work trains a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs, and in contrast to the popular depth-from-single-image networks, DeMoN learns the concept of matching and better generalizes to structures not seen during training.
Lucid Data Dreaming for Object Tracking
TLDR
This work proposes a new training strategy which achieves state-of-the-art results across three evaluation datasets while using 20x ~ 100x less annotated data than competing methods, and generates in-domain training data using the provided annotation on the first frame of each video to synthesize ("lucid dream") plausible future video frames.
Uncertainty Estimates and Multi-hypotheses Networks for Optical Flow
TLDR
A new network architecture and loss function is introduced that enforce complementary hypotheses and provide uncertainty estimates efficiently with a single forward pass and without the need for sampling or ensembles.
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
TLDR
This work introduces Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and reconstruction of high-quality 3D shapes without prohibitive memory requirements, and demonstrates the effectiveness and generalization power of this representation.
Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
TLDR
This work presents an approach that involves the prediction of several samples of the future with a winner-takes-all loss and iterative grouping of samples to multiple modes and shows on synthetic and real data that the proposed approach triggers good estimates of multimodal distributions and avoids mode collapse.
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
TLDR
An efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow is presented and the estimated occlusions and motion boundaries clearly improve over the state-of-the-art.
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
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.
...
...