AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
This study proposes the use of edge-based features within the GANs framework to efficiently reduce feature redundancy during training, which mitigates artifact-related issues and improves image quality but also underscores the significant impact of feature redundancy on the learning process of GAN-based image denoising models.
This work proposes a new GAN-based face hallucination method primarily based on the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN), and presents a personalised adaptation of ESRGAN that employs the VGG16 architecture with a compact pre-trained version.
This work identifies direct output access to the image statistics being corrected as a key factor governing when adversarial post-training succeeds, the first systematic study of adversarial post-training for pixel diffusion.
A hybrid GAN-guided diffusion framework that uses a pretrained Wasserstein GAN with gradient penalty (WGAN-GP) as a feature prior for conditional diffusion-based image restoration that consistently improves the quality of both degraded and low-resolution images.
Both numerical results and visual evaluations confirm that the proposed framework provides a balanced solution for preserving structural details while maintaining perceptual realism in image inpainting applications.
The method employs a lightweight UNet architecture based on depthwise separable convolutions, substantially reducing the parameter count while decreasing inference steps from 1000 to 20 through a fast sampling strategy, exhibiting excellent quality-efficiency trade-offs.
A CNN-based edge-aware artifact reduction framework (CNN-AR) is proposed that integrates an enhanced deep super-resolution (EDSR) backbone with a holistically nested edge detection (HED) guided loss, enabling superior artifact suppression while preserving fine structural details.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.