Z
Zhibo Chen
Researcher at University of Science and Technology of China
Publications - 374
Citations - 6048
Zhibo Chen is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Image quality. The author has an hindex of 27, co-authored 344 publications receiving 3385 citations. Previous affiliations of Zhibo Chen include Sony Broadcast & Professional Research Laboratories & Microsoft.
Papers
More filters
Posted Content
Conditional Image-to-Image Translation
TL;DR: In this paper, a new problem, conditional image-to-image translation, is introduced, which is to translate an image from the source domain to the target domain conditioned on a given image in a target domain.
Journal ArticleDOI
Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation
TL;DR: DosGAN as discussed by the authors treats domain information as explicit supervision and design an unpaired image-to-image translation framework, which takes the first step towards the exploration of explicit domain supervision.
Proceedings ArticleDOI
Progressive Image Inpainting with Full-Resolution Residual Network
TL;DR: Zhang et al. as discussed by the authors proposed full-resolution residual network (FRRN) to fill irregular holes, which is proved to be effective for progressive image inpainting, and adopted N Blocks, One Dilation strategy, which assigns several residual blocks for one dilation step.
Book ChapterDOI
TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images
TL;DR: TuiGAN as discussed by the authors is a generative model that is trained on only two unpaired images and amounts to one-shot unsupervised learning, where an image is translated in a coarse-to-fine manner where the generated image is gradually refined from global structures to local details.
Book ChapterDOI
Global Distance-Distributions Separation for Unsupervised Person Re-identification
TL;DR: In this paper, a global distance-distributions separation (GDS) constraint over the two distributions is introduced to encourage the clear separation of positive and negative samples from a global view.