In this work, we propose GFPGAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via novel channel-split spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real world datasets.

2021: Xintao Wang, Yu Li, Honglun Zhang, Ying Shan

https://arxiv.org/pdf/2101.04061v2.pdf

Mask classification is sufficiently general to solve both semantic and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure.

2021: Bowen Cheng, A. Schwing and Alexander Kirillov

https://arxiv.org/pdf/2107.06278v1.pdf