Yujiu Yang

TL;DR: TediGAN as discussed by the authors uses StyleGAN inversion module, visual-linguistic similarity learning, and instance-level optimization to produce diverse and high-quality images with an unprecedented resolution at 10242.

TL;DR: This work proposes to conduct filter selection and filter learning simultaneously, in a unified model, and defines a factorized convolutional filter (FCF), consisting of a standard real-valued convolutionan filter and a binary scalar, as well as a dot-product operator between them.

TL;DR: An efficient algorithm is developed by equivalently reformulating the MIP problem as a continuous optimization problem to jointly optimize the binary selection factors and continuous perturbation magnitudes of all pixels, with a cardinality constraint on selection factors to explicitly control the degree of sparsity.

TL;DR: In this paper , a pre-trained StyleGAN is used to generate high-resolution video and audio for one-shot talking face generation, where the latent feature space of a StyleGAN was investigated and some excellent spatial transformation properties were discovered.

TL;DR: The NTIRE 2021 challenge on perceptual image quality assessment (IQA) as discussed by the authors was held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.