F
Feng Liu
Researcher at Portland State University
Publications - 104
Citations - 7558
Feng Liu is an academic researcher from Portland State University. The author has contributed to research in topics: Motion estimation & Image warping. The author has an hindex of 36, co-authored 102 publications receiving 5976 citations. Previous affiliations of Feng Liu include Wisconsin Alumni Research Foundation & Zhejiang University.
Papers
More filters
Proceedings ArticleDOI
Video Frame Interpolation via Adaptive Separable Convolution
Simon Niklaus,Long Mai,Feng Liu +2 more
TL;DR: In this article, a deep fully convolutional neural network is proposed to estimate pairs of 1D kernels for all pixels simultaneously, which allows for the incorporation of perceptual loss to train the network to produce visually pleasing frames.
Journal ArticleDOI
Content-preserving warps for 3D video stabilization
TL;DR: A technique that transforms a video from a hand-held video camera so that it appears as if it were taken with a directed camera motion, and develops algorithms that can effectively recreate dynamic scenes from a single source video.
Proceedings ArticleDOI
Leveraging stereopsis for saliency analysis
TL;DR: This paper explores stereopsis for saliency analysis and presents two approaches to stereo saliency detection from stereoscopic images, one based on the global disparity contrast in the input image and one that leverages domain knowledge in stereoscopic photography.
Proceedings ArticleDOI
Context-Aware Synthesis for Video Frame Interpolation
Simon Niklaus,Feng Liu +1 more
TL;DR: A context-aware synthesis approach that warps not only the input frames but also their pixel-wise contextual information and uses them to interpolate a high-quality intermediate frame and outperforms representative state-of-the-art approaches.
Journal ArticleDOI
Subspace video stabilization
TL;DR: This article focuses on the problem of transforming a set of input 2D motion trajectories so that they are both smooth and resemble visually plausible views of the imaged scene, and offers the first method that both achieves high-quality video stabilization and is practical enough for consumer applications.