Tuesday 20 Nov, 2012 at 5:50 pm in Smart Room 9-105 SSE. Abstract A variety of dynamic objects, such as faces, bodies, and cloth, are represented in computer vision and computer graphics as a collection of moving spatial landmarks. A number of tasks are performed on this type of data such as character animation, motion [...]
Our joint research project with Iain Matthews at Disney Research Pittsburgh and Yaser Sheikh and Tomas Simon at Carnegie Mellon University is covered by Carnegie Mellon News. To quote from the press release: Computer graphic artists who produce computer-animated movies and games spend much time creating subtle movements such as expressions on faces, gesticulations on [...]
The Computer Vision Lab hosted a rigorous summer internship program for undergraduate students. Sophomore, Junior and Senior interns worked for 2 months in the lab, under the supervision of faculty and PhD students. The students worked both individually and in groups, on a range of ideas, from making a campus 3D model to automatic generation [...]
M Haris Baig, who did his senior project in CV lab and also is a co-author on our ICCV 2011 paper, has received a fully funded PhD offer from Univ of Dartmouth, where he will be joining this Fall. He will be working with Lorenzo Torresani, who has pioneering work in the field of nonrigid [...]
Maheen Rashid, a CV Lab research assistant since 2011, who earlier also did her senior project in our lab, has received a Fulbright scholarship and has joined Robotics Institute at Carnegie Mellon University for her Ph.D. studies. Maheen worked on Single View Reconstruction during her research assistantship here, and has coauthored our ECCV 2012 paper [...]
Group Photo, a project at CV Lab by Aamer Zaheer, Ali Rehan, Abdur Rehman Naeem and Maria Zubair, won the first position at Startup Weekend Lahore. Group Photo android app solved the age-old problem that while taking a photograph of a group of friends, the photographer is missed out in the picture. The app, which [...]
This paper presents a new Shape-from-X method which is applicable for typical man-made environments which have a profusion of orthogonal lines. A full single-view reconstruction method for multi-planar man-made scenes is demonstrated. Authors: Aamer Zaheer, Maheen Rashid, Sohaib Khan, ECCV 2012.
Murtaza Taj, Andrea Cavallaro International Conference on Image Processing, ICIP 2012 Abstract We present an event recognition framework to detect interactions among objects, for example people, using a network of cameras and associated microphone pairs. The complementarity of the video and audio modalities is exploited to cover wide areas. In particular, object movements in portions of the scene that [...]
Our paper in ACM Transactions on Graphics April 2012 presents a fundamentally new way to model time-varying point clouds, that dramatically reduces processing times for common graphics pipeline tasks such as labeling, gap-filling, denoising, and motion touch-up. This is joint work with Carnegie Mellon University and Disney Research Pittsburgh, and has been presented at Siggraph 2012.
Arif Mahmood, Sohaib Khan IEEE Transactions on Image Processing, Vol 21, No 4, April 2012 Abstract Partial computation elimination techniques are often used for fast template matching. At a particular search location, computations are prematurely terminated as soon as it is found that this location cannot compete already known best-match location. Due to non-monotonic growth [...]
Aamer Zaheer, Ijaz Akhter, Mohammad Haris Baig, Shabbir Marzban, Sohaib Khan International Conference on Computer Vision, ICCV, 2011 Abstract Most nonrigid objects exhibit temporal regularities in their deformations. Recently it was proposed that these regularities can be parameterized by assuming that the non- rigid structure lies in a small dimensional trajectory space. In this paper, [...]
Ijaz Akhter, Yaser Sheikh, Sohaib Khan, Takeo Kanade IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 33, No 7, Jul 2011 Abstract Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes. These basis are object dependent and therefore have [...]