This paper presents a robust and flexible framework for augmented reality which does not require instrumenting either the environment or the workpiece. A model-based visual track...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
A novel framework for spatially estimating unknown image data is presented. Common applications include inpainting, concealment of transmission errors, prediction in video coding,...
Haricharan Lakshman, Patrick Ndjiki-Nya, Martin K&...
—In this paper, we address the super resolution (SR) problemfromasetofdegradedlowresolution(LR)imagestoobtain a high resolution (HR) image. Accurate estimation of the sub-pixel m...
S. Derin Babacan, Rafael Molina, Aggelos K. Katsag...
Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...