Simultaneous Face Alignment
Paper X. Cheng, S. Sridharan, J. Saragih, and S. Lucey, “Anchored Deformable Face Ensemble Alignment”, 5th NORDIA Workshop at the European Conference on Computer Vision (ECCV) 2012. [Paper] X.Cheng, S. Sridharan, C. Fookes, J. Saragih and S. Lucey, “Deformable Face Ensemble Alignment with Robust Grouped-L1 Anchors”,...
Featureless Computer Vision
Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good performance in a myriad of visual classification tasks. A central question in the vision, learning and neuroscience communities regards why these architectures perform so well.
This project aims to take a unique perspective...
Structure from Motion
Trajectory basis Non-Rigid Structure From Motion
(NRSFM) currently faces two problems: the limit of reconstructability and the need to tune the basis size for different
sequences. This paper provides a novel theoretical bound
on 3D reconstruction error, arguing that the existing deﬁ-
nition of reconstructability is fundamentally ﬂawed in...