Patrick Knöbelreiter

  • Citations Per Year
Learn More
Demosaicing is an important first step for color image acquisition. For practical reasons, demosaicing algorithms have to be both efficient and yield high quality results in the presence of noise. The demosaicing problem poses several challenges, e.g. zippering and false color artifacts as well as edge blur. In this work, we introduce a novel learning based(More)
We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expressive features for matching and distinctive color edges, which in turn are used to compute the unary and(More)
Virtual fly-through animations through computer generated models are a strong tool to convey properties and the appearance of these models. In, e.g., architectural models the big advantage of such a fly-through animation is that it is possible to convey the structure of the model easily. However, the path generation is not always trivial, to get a good(More)
We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). We tackle the computationand memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to(More)
In this work we tackle the problem of semantic image segmentation with a combination of convolutional neural networks (CNNs) and conditional random fields (CRFs). The CRF takes contrast sensitive weights in a local neighborhood as input (pairwise interactions) to encourage consistency (smoothness) within the prediction and align our segmentation boundaries(More)
  • 1