Progressively Unfreezing Perceptual GAN
This work addresses texture detail generation in GANs for image generation tasks, representing an incremental improvement with specific gains.
The paper tackles the problem of GAN-generated images lacking texture details by proposing PUPGAN, a framework that uses an adaptive perceptual discriminator and progressively unfreezing scheme, resulting in superior performance on three image generation tasks compared to classical baselines.
Generative adversarial networks (GANs) are widely used in image generation tasks, yet the generated images are usually lack of texture details. In this paper, we propose a general framework, called Progressively Unfreezing Perceptual GAN (PUPGAN), which can generate images with fine texture details. Particularly, we propose an adaptive perceptual discriminator with a pre-trained perceptual feature extractor, which can efficiently measure the discrepancy between multi-level features of the generated and real images. In addition, we propose a progressively unfreezing scheme for the adaptive perceptual discriminator, which ensures a smooth transfer process from a large scale classification task to a specified image generation task. The qualitative and quantitative experiments with comparison to the classical baselines on three image generation tasks, i.e. single image super-resolution, paired image-to-image translation and unpaired image-to-image translation demonstrate the superiority of PUPGAN over the compared approaches.