1 code implementation • 9 Sep 2019 • Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler, Stefan Roth
When adding our network layer to state-of-the-art networks for optical flow and semantic segmentation, boundary artifacts are removed and the accuracy is improved.
2 code implementations • 17 Aug 2018 • Mohamed Omran, Christoph Lassner, Gerard Pons-Moll, Peter V. Gehler, Bernt Schiele
Direct prediction of 3D body pose and shape remains a challenge even for highly parameterized deep learning models.
Ranked #1 on Monocular 3D Human Pose Estimation on Human3.6M (Use Video Sequence metric)
1 code implementation • ICCV 2017 • Raghudeep Gadde, Varun Jampani, Peter V. Gehler
A key insight of this work is that fast optical flow methods can be combined with many different CNN architectures for improved performance and end-to-end training.
no code implementations • 24 Jul 2017 • Yinghao Huang, Federica Bogo, Christoph Lassner, Angjoo Kanazawa, Peter V. Gehler, Ijaz Akhter, Michael J. Black
Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios.
1 code implementation • ICCV 2017 • Christoph Lassner, Gerard Pons-Moll, Peter V. Gehler
We present the first image-based generative model of people in clothing for the full body.
2 code implementations • CVPR 2017 • Christoph Lassner, Javier Romero, Martin Kiefel, Federica Bogo, Michael J. Black, Peter V. Gehler
With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body.
Ranked #1 on Monocular 3D Human Pose Estimation on Human3.6M (Use Video Sequence metric)
3D human pose and shape estimation Monocular 3D Human Pose Estimation
no code implementations • CVPR 2017 • Varun Jampani, Raghudeep Gadde, Peter V. Gehler
We propose a 'Video Propagation Network' that processes video frames in an adaptive manner.
Ranked #72 on Semi-Supervised Video Object Segmentation on DAVIS 2016
1 code implementation • CVPR 2017 • Thomas Nestmeyer, Peter V. Gehler
Our results show a simple pixel-wise decision, without any context or prior knowledge, is sufficient to provide a strong baseline on IIW.
no code implementations • 21 Jun 2016 • Raghudeep Gadde, Varun Jampani, Renaud Marlet, Peter V. Gehler
This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades.
1 code implementation • 20 Nov 2015 • Raghudeep Gadde, Varun Jampani, Martin Kiefel, Daniel Kappler, Peter V. Gehler
We introduce a new 'bilateral inception' module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image.
no code implementations • CVPR 2016 • Varun Jampani, Martin Kiefel, Peter V. Gehler
The ability to learn more general forms of high-dimensional filters can be used in several diverse applications.
no code implementations • 20 Dec 2014 • Martin Kiefel, Varun Jampani, Peter V. Gehler
This paper presents a convolutional layer that is able to process sparse input features.
no code implementations • CVPR 2014 • Andreas M. Lehrmann, Peter V. Gehler, Sebastian Nowozin
The use of hidden variables makes them expressive models, but inference is only approximate and requires procedures such as particle filters or Markov chain Monte Carlo methods.
1 code implementation • 4 Feb 2014 • Varun Jampani, Sebastian Nowozin, Matthew Loper, Peter V. Gehler
Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion.
no code implementations • NeurIPS 2011 • Carsten Rother, Martin Kiefel, Lumin Zhang, Bernhard Schölkopf, Peter V. Gehler
We address the challenging task of decoupling material properties from lighting properties given a single image.