Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video
The past few years have witnessed fast development in video quality enhancement via deep learning. Existing methods mainly focus on enhancing the objective quality of compressed video while ignoring its perceptual quality. In this paper, we focus on enhancing the perceptual quality of compressed video. Our main observation is that enhancing the perceptual quality mostly relies on recovering high-frequency sub-bands in wavelet domain. Accordingly, we propose a novel generative adversarial network (GAN) based on multi-level wavelet packet transform (WPT) to enhance the perceptual quality of compressed video, which is called multi-level wavelet-based GAN (MW-GAN). In MW-GAN, we first apply motion compensation with a pyramid architecture to obtain temporal information. Then, we propose a wavelet reconstruction network with wavelet-dense residual blocks (WDRB) to recover the high-frequency details. In addition, the adversarial loss of MW-GAN is added via WPT to further encourage high-frequency details recovery for video frames. Experimental results demonstrate the superiority of our method.
Code (1)
Tasks
Generative Adversarial NetworkMotion CompensationSimilar Papers 제목 키워드 기반
Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolution
In single image super-resolution (SISR), given a low-resolution (LR) image, one wishes to find a high-resolution (HR) version of it which is both accurate and photo-realistic. Recently, it has been shown that there exist…
Generative Adversarial NetworkImage Super-ResolutionStyle TransferSuper-ResolutionWaveFill: A Wavelet-based Generation Network for Image Inpainting
Image inpainting aims to complete the missing or corrupted regions of images with realistic contents. The prevalent approaches adopt a hybrid objective of reconstruction and perceptual quality by using generative adversa…
Image InpaintingAWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis
Lung ultrasound (LUS) is a safe and portable imaging modality, but the scarcity of data limits the development of machine learning methods for image interpretation and disease monitoring. Existing generative augmentation…
Multi-scale Generative Modeling for Fast Sampling
While working within the spatial domain can pose problems associated with ill-conditioned scores caused by power-law decay, recent advances in diffusion-based generative models have shown that transitioning to the wavele…
Learning Bone Suppression from Dual Energy Chest X-rays using Adversarial Networks
Suppressing bones on chest X-rays such as ribs and clavicle is often expected to improve pathologies classification. These bones can interfere with a broad range of diagnostic tasks on pulmonary disease except for muscul…
Bone Suppression From Dual Energy Chest X-RaysDiagnosticGenerative Adversarial Network