X
Xiaoqiang Zhou
Researcher at University of Science and Technology of China
Publications - 4
Citations - 17
Xiaoqiang Zhou is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Autoencoder & Inpainting. The author has an hindex of 1, co-authored 4 publications receiving 3 citations.
Papers
More filters
Proceedings ArticleDOI
Free-Form Image Inpainting via Contrastive Attention Network
TL;DR: Li et al. as mentioned in this paper proposed a self-supervised Siamese inference network to improve the robustness and generalization of deep learning based image inpainting approaches, which can encode contextual semantics from full resolution images and obtain more discriminative representations.
Journal ArticleDOI
Contrastive Attention Network with Dense Field Estimation for Face Completion
TL;DR: Li et al. as discussed by the authors proposed a self-supervised Siamese inference network to improve the generalization and robustness of encoders, which can encode contextual semantics from full-resolution images and obtain more discriminative representations.
Posted Content
Free-Form Image Inpainting via Contrastive Attention Network.
TL;DR: A self-supervised Siamese inference network that can encode contextual semantics from full resolution images and obtain more discriminative representations and a multi-scale decoder with a novel dual attention fusion module (DAF), which can combine both the restored and known regions in a smooth way.
Proceedings ArticleDOI
Image Inpainting with Contrastive Relation Network
TL;DR: Zhang et al. as discussed by the authors proposed a two-stage inpainting framework to address the two requirements in two separate stages, where the corrupted image is firstly predicted through segmentation reconstruction network, while fine-grained image details are restored in the second stage through an image generator.