D
Deqing Sun
Researcher at Google
Publications - 102
Citations - 11830
Deqing Sun is an academic researcher from Google. The author has contributed to research in topics: Optical flow & Computer science. The author has an hindex of 36, co-authored 85 publications receiving 8189 citations. Previous affiliations of Deqing Sun include Max Planck Society & Brown University.
Papers
More filters
Proceedings ArticleDOI
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
TL;DR: PWC-Net as discussed by the authors uses the current optical flow estimate to warp the CNN features of the second image, which is processed by a CNN to estimate the optical flow, and achieves state-of-the-art performance on the MPI Sintel final pass and KITTI 2015 benchmarks.
Proceedings ArticleDOI
Secrets of optical flow estimation and their principles
TL;DR: It is discovered that “classical” flow formulations perform surprisingly well when combined with modern optimization and implementation techniques, and while median filtering of intermediate flow fields during optimization is a key to recent performance gains, it leads to higher energy solutions.
Proceedings ArticleDOI
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Hang Su,Varun Jampani,Deqing Sun,Subhransu Maji,Evangelos Kalogerakis,Ming-Hsuan Yang,Jan Kautz +6 more
TL;DR: A network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice that outperforms existing state-of-the-art techniques on 3D segmentation tasks.
Proceedings ArticleDOI
Blind Image Deblurring Using Dark Channel Prior
TL;DR: This work introduces a linear approximation of the min operator to compute the dark channel and achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.
Proceedings ArticleDOI
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
TL;DR: In this paper, an end-to-end convolutional neural network is proposed for variable-length multi-frame video interpolation, where the motion interpretation and occlusion reasoning are jointly modeled.