Xuehui Wang

TL;DR: The AIM 2020 challenge on efficient single image super-resolution was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images with focus on the proposed solutions and results.

TL;DR: A computation efficient yet accurate network based on the proposed attentive auxiliary features (A$^2$F) for SISR that outperforms SOTA methods for all scales, which proves its ability to better utilize the auxiliary features.

TL;DR: Zhang et al. as mentioned in this paper proposed a noise prior learner NEGAN to simulate the noise distribution of real legacy photos using unpaired images, which mainly focuses on matching highfrequency parts of noisy images through discrete wavelet transform (DWT) since they include most of noise statistics.

TL;DR: In this paper, the auxiliary features from all the previous layers are projected into a common space and channel attention is employed to select the most important common feature based on current layer feature.

TL;DR: This paper proposes a new method, named ContrastMask, which learns a mask segmentation model on both base and novel categories under a unified pixel-level contrastive learning framework, and demonstrates the superiority of this method, which outperforms previous state-of-the-arts methods.