D
Dongxiao Li
Researcher at Zhejiang University
Publications - 96
Citations - 978
Dongxiao Li is an academic researcher from Zhejiang University. The author has contributed to research in topics: Depth map & Rendering (computer graphics). The author has an hindex of 14, co-authored 92 publications receiving 796 citations.
Papers
More filters
Journal ArticleDOI
Identifying Facemask-Wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19
Bosheng Qin,Dongxiao Li +1 more
TL;DR: A new facemask-wearing condition identification method by combining image super-resolution and classification networks (SRCNet), which quantifies a three-category classification problem based on unconstrained 2D facial images, thus having potential applications in epidemic prevention involving COVID-19.
Journal ArticleDOI
Fast stereo matching using adaptive guided filtering
TL;DR: A novel stereo matching algorithm is presented that ranks the 10th among about 152 algorithms on the Middlebury stereo evaluation benchmark, and takes the 1st place in all local methods.
Proceedings ArticleDOI
A Depth Extraction Method Based on Motion and Geometry for 2D to 3D Conversion
TL;DR: This paper proposes a novel depth extraction method based on motion and geometric information for 2D to 3D conversion, which consists of two major depth extraction modules, the depth from motion and depth from geometrical perspective.
Journal ArticleDOI
Architecture Design for H.264/AVC Integer Motion Estimation with Minimum Memory Bandwidth
Dongxiao Li,Wei Zheng,Ming Zhang +2 more
TL;DR: A novel memory-access and computation efficient full-search block-matching hardware architecture that can achieve the minimum off-chip memory bandwidth and the maximum computational performance for H.264/AVC integer motion estimation is presented.
Journal ArticleDOI
Full-Image Guided Filtering for Fast Stereo Matching
TL;DR: A novel full-image guided filtering method is proposed that fulfills the requirements of edge preserving and low complexity and is applied to the cost-volume filtering in the local stereo matching framework.