Yuntao Wu

TL;DR: The NTIRE 2021 depth guided image relighting challenge as mentioned in this paper focused on one-to-one relighting where the goal is to transform the illumination setup of an input image (color temperature and light source position) to the target illumination setup.

TL;DR: In this article, the authors propose novel down-sampling feature self-calibrated block (DFSB) and up-sampled feature self calibrated block (UFSB) as the basic blocks of feature encoder and decoder to calibrate feature representation.

TL;DR: An Enhanced Discriminative Generative Adversarial Network (EDGAN) for SR facial recognition to achieve better reconstruction and perceptual fidelities is presented and it is discovered that a versatile D boosts the adversarial framework to a preferable Nash equilibrium.

TL;DR: A novel cross-task feature alignment method that imposes four feature alignment layers before the feature fusing and sharing step in multi-task learning period to align the scale and channel of features across tasks and fine-tune feature representation iteratively is proposed.

TL;DR: Wang et al. as discussed by the authors proposed a context-aware based discriminative siamese neural network for face verification, which used a contextaware module to anchor facial structure information by filtering out irrelevant information.