This paper presents a first investigation on the structure from motion problem from the combination of full and weak perspective images. This problem arises in multiresolution obj...
We describe a learning-based method for low-level vision problems--estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, m...
We present a novel variational approach to top-down image segmentation, which accounts for significant projective transformations between a single prior image and the image to be s...
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
Detection of humans and estimation of their 2D poses from a single image are challenging tasks. This is especially true when part of the observation is occluded. However, given a l...