no code implementations • 20 Apr 2022 • David Griffiths, Tobias Ritschel, Julien Philip
We propose a relighting method for outdoor images.
no code implementations • 2 Dec 2020 • David Griffiths, Jan Boehm, Tobias Ritschel
This can be overcome by a novel form of training, where an additional network is employed to steer the optimization itself to explore the entire parameter space i. e., to be curious, and hence, to resolve those ambiguities and find workable minima.
1 code implementation • ECCV 2020 • David Griffiths, Jan Boehm, Tobias Ritschel
As we assume the scene not to be labeled by centers, no classic loss, such as Chamfer can be used to train it.
no code implementations • 10 Jul 2019 • David Griffiths, Jan Boehm
With deep learning becoming a more prominent approach for automatic classification of three-dimensional point cloud data, a key bottleneck is the amount of high quality training data, especially when compared to that available for two-dimensional images.
no code implementations • 9 Jul 2019 • David Griffiths, Jan Boehm
In this paper we review the current state-of-the-art deep learning architectures for processing unstructured Euclidean data.
no code implementations • 8 Apr 2019 • David Griffiths, Jan Boehm
Recent developments in the field of deep learning for 3D data have demonstrated promising potential for end-to-end learning directly from point clouds.