We address the problem of reconstructing 3D face models from large unstructured photo collections, e.g., obtained by Google image search or from personal photo collections in iPho...
Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
Sudheendra Vijayanarasimhan (University of Texas a...
This paper addresses the reconstruction of high resolution omnidirectional images from a low resolution video acquired by an omnidirectional camera moving in a static scene. In or...
Luigi Bagnato, Yannick Boursier, Pascal Frossard, ...
This paper presents a new method for the incremental integration of overlapped range images. It is assumed thatframe transformations between all pairs of views can be reliably com...
Humans have an amazing ability to instantly grasp the overall 3D structure of a scene – ground orientation, relative positions of major landmarks, etc – even from a single ima...