X
Xian Wu
Researcher at Tsinghua University
Publications - 16
Citations - 393
Xian Wu is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 7, co-authored 11 publications receiving 255 citations.
Papers
More filters
Journal ArticleDOI
A survey of image synthesis and editing with generative adversarial networks
Xian Wu,Kun Xu,Peter Hall +2 more
TL;DR: This paper surveys recent GAN papers regarding topics including, but not limited to, texture synthesis, image inpainting, image-to-image translation, and image editing.
Journal ArticleDOI
PatchTable: efficient patch queries for large datasets and applications
TL;DR: A data structure that reduces approximate nearest neighbor query times for image patches in large datasets by up to 9× over k-coherence, up to 12× over TreeCANN, and up to 200× over PatchMatch is presented.
Journal ArticleDOI
Deep-Learning Detection of Cancer Metastases to the Brain on MRI
Min Zhang,Geoffrey S. Young,Huai Chen,Huai Chen,Jing Li,Jing Li,Lei Qin,J Ricardo McFaline-Figueroa,David A. Reardon,Xinhua Cao,Xian Wu,Xiaoyin Xu +11 more
TL;DR: Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective.
Journal ArticleDOI
Robust background identification for dynamic video editing
TL;DR: A new, practical method that can reliably identify background features in complex video, leading to accurate camera path estimation and background layering, and can be directly used to improve common video editing applications such as stabilization, compositing and background reconstruction.
Journal ArticleDOI
Deep Portrait Image Completion and Extrapolation
TL;DR: Li et al. as discussed by the authors proposed a two-stage deep learning framework for solving the problem of general image completion and extrapolation on portrait images, where the first stage extracts a complete, coherent human body structure through a human parsing network, which focuses on structure recovery inside the unknown region with the help of full-body pose estimation.