X
Xiaoyun Zhang
Researcher at Shanghai Jiao Tong University
Publications - 108
Citations - 2631
Xiaoyun Zhang is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Motion estimation & Encoder. The author has an hindex of 17, co-authored 106 publications receiving 1418 citations.
Papers
More filters
Proceedings ArticleDOI
DVC: An End-To-End Deep Video Compression Framework
TL;DR: This paper proposes the first end-to-end video compression deep model that jointly optimizes all the components for video compression, and shows that the proposed approach can outperform the widely used video coding standard H.264 in terms of PSNR and be even on par with the latest standard MS-SSIM.
Proceedings ArticleDOI
Depth-Aware Video Frame Interpolation
TL;DR: DAIN as mentioned in this paper proposes a depth-aware flow projection layer to synthesize intermediate flows that preferably sample closer objects than farther ones, and then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels.
Posted Content
Depth-Aware Video Frame Interpolation
TL;DR: A video frame interpolation method which explicitly detects the occlusion by exploring the depth information, and develops a depth-aware flow projection layer to synthesize intermediate flows that preferably sample closer objects than farther ones.
Posted Content
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
TL;DR: A novel adaptive warping layer is developed to integrate both optical flow and interpolation kernels to synthesize target frame pixels and is fully differentiable such that both the flow and kernel estimation networks can be optimized jointly.
Journal ArticleDOI
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
TL;DR: In this article, a novel adaptive warping layer is developed to integrate both optical flow and interpolation kernels to synthesize target frame pixels, which is fully differentiable such that both the flow and kernel estimation networks can be optimized.