I am currently working at Harvard University as a postdoctoral fellow with Dr. Hanspeter Pfister in the visual computing group. I obtained my Ph.D in Computer Science at Brown University in 2012. At Brown I worked with Dr. Michael J. Black and Dr. Erik B. Sudderth, on Computer Vision and Machine Learning. I am particularly interested in optical flow estimation, motion segmentation, layered model, and motion-based video enhancement.
For updates, please see my webpage at Harvard.
Recent papers ( My Google scholar profile)
IJCV preprint: " A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them"
[Matlab code], [From publisher].
TPAMI preprint: " On Bayesian Adaptive Video Super Resolution".
CVPR 2013: "A Fully-Connected Layered Model of Foreground and Background Flow" [Sup. Mat.], Code available upon request (for research purposes only).
ECCV 2012: "Non-causal Temporal Prior for Video Deblocking" [Sup. Mat.].
Dissertation: "From Pixels to Layers: Joint Motion Estimation and Segmentation" .
CVPR 2012: "Layered Segmentation and Optical Flow Estimation Over Time" [Sup. Mat.], [Poster], [Data].
CVPR 2011: "A Bayesian Approach to Adaptive Video Super Resolution".
NIPS 2010: "Layered Image Motion with Explicit Occlusions, Temporal Consistency, and Depth Ordering" [Spotlight], [Poster].
CVPR 2010: "Secrets of Optical Flow Estimation and Their Principles" [MATLAB code], [CIFAR talk slides], [Results on Middlebury training set], [Spotlight], [Poster].
ECCV 2008: "Learning Optical Flow" [Talk slides], [Extra training data].