Weize Quan

TL;DR: A novel three-stage inpainting framework with local and global refinement that outperforms the state of the arts on three popular publicly available datasets for image inpaintedting and can be directly inserted into the end of any existing networks to further improve their inPainting performance.

TL;DR: Wang et al. as discussed by the authors proposed a new center voting strategy based on the relative geometric relationship between the object center and point pair features, which generates votes to object centers resulting in vote clusters near real object centers and then aggregates these votes to generate a set of pose hypotheses.

TL;DR: A novel deep learning framework that derives discriminative local descriptors for 3D surface shapes by leveraging a triplet network to perform deep metric learning, which takes a set of triplets as input and is minimized to distinguish between similar and dissimilar pairs of keypoints.

TL;DR: This work proposes a convolutional neural network (CNN)-based model to distinguish computergenerated images from natural images (NIs) with channel and pixel correlation and considers the generality of the network (or subnetwork), i.e., the newly introduced hybrid correlation module.