← Search

Harald Kosch

2 accepted papers

2019

Incremental Scene Synthesis

NeurIPS 2019poster

We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be…

Cited by 9SourcePDFScholar
2019

Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition

IROS 2019poster

While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. Therefore, it has become common practice to use available synthetic samples along domain adaptation schemes to prep…

Cited by 14SourceScholar