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 • 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
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 • Jun Xie, Martin Kiefel, Ming-Ting Sun, Andreas Geiger
Semantic annotations are vital for training models for object recognition, semantic segmentation or scene understanding.
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 • 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.