1 code implementation • 17 Jan 2024 • Benjamin Ummenhofer, Sanskar Agrawal, Rene Sepulveda, Yixing Lao, Kai Zhang, Tianhang Cheng, Stephan Richter, Shenlong Wang, German Ros
Reconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also to the new lighting conditions and yet evaluations of inverse rendering methods rely on novel view synthesis data or simplistic synthetic datasets for quantitative analysis.
1 code implementation • 12 Oct 2022 • Lukas Prantl, Benjamin Ummenhofer, Vladlen Koltun, Nils Thuerey
We present a novel method for guaranteeing linear momentum in learned physics simulations.
no code implementations • CVPR 2022 • Anirud Thyagharajan, Benjamin Ummenhofer, Prashant Laddha, Om Ji Omer, Sreenivas Subramoney
3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR.
no code implementations • 16 Nov 2021 • Anirud Thyagharajan, Benjamin Ummenhofer, Prashant Laddha, Om J Omer, Sreenivas Subramoney
3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR.
no code implementations • ICCV 2021 • Benjamin Ummenhofer, Vladlen Koltun
We propose generalized convolutional kernels for 3D reconstruction with ConvNets from point clouds.
no code implementations • ICLR 2020 • Benjamin Ummenhofer, Lukas Prantl, Nils Thuerey, Vladlen Koltun
We present an approach to Lagrangian fluid simulation with a new type of convolutional network.
1 code implementation • CVPR 2019 • Jose M. Facil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model.
1 code implementation • ECCV 2018 • Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
For mapping, we accumulate information in a cost volume centered at the current depth estimate.
2 code implementations • CVPR 2017 • Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig, Nikolaus Mayer, Eddy Ilg, Alexey Dosovitskiy, Thomas Brox
In this paper we formulate structure from motion as a learning problem.
no code implementations • ICCV 2015 • Benjamin Ummenhofer, Thomas Brox
We present a variational approach for surface reconstruction from a set of oriented points with scale information.