The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
This paper presents an effective strategy to extract the buildings and to reconstruct 3-D buildings using high-resolution multispectral stereo satellite images. Proposed scheme con...
Dimensionality reduction plays an important role in many machine learning and pattern recognition tasks. In this paper, we present a novel dimensionality reduction algorithm calle...
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
—When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstru...