S
Shengyang Dai
Researcher at Google
Publications - 35
Citations - 1581
Shengyang Dai is an academic researcher from Google. The author has contributed to research in topics: Image segmentation & Pixel. The author has an hindex of 18, co-authored 34 publications receiving 1438 citations. Previous affiliations of Shengyang Dai include Microsoft & Princeton University.
Papers
More filters
Proceedings ArticleDOI
Soft Edge Smoothness Prior for Alpha Channel Super Resolution
TL;DR: A novel combination of this soft edge smoothness prior and the alpha matting technique for color image super resolution, by normalizing edge segments with their alpha channel description, to achieve a unified treatment of edges with different contrast and scale.
Journal ArticleDOI
SoftCuts: A Soft Edge Smoothness Prior for Color Image Super-Resolution
TL;DR: A novel combination of this soft edge smoothness prior and the alpha matting technique for color image SR, by adaptively normalizing image edges according to their alpha-channel description leads to the adaptive SoftCuts algorithm, which represents a unified treatment of edges with different contrasts and scales.
Proceedings ArticleDOI
Motion from blur
Shengyang Dai,Ying Wu +1 more
TL;DR: A major contribution of this paper is a new finding of an elegant motion blur constraint, exhibiting a very similar mathematical form as the optical flow constraint, that applies locally to pixels in the image.
Proceedings ArticleDOI
A novel white blood cell segmentation scheme using scale-space filtering and watershed clustering
TL;DR: A novel white blood cell segmentation scheme using scale-Space filtering and watershed clustering and feature space clustering that can effectively extract various WBC regions from cell images of peripheral blood smear is proposed.
Proceedings ArticleDOI
Bilateral Back-Projection for Single Image Super Resolution
TL;DR: The back-projection process can be guided by the edge information to avoid across-edge smoothing, thus the chessboard effect and ringing effect along image edges are removed and promising results can be obtained.