Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
We introduce SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. Leveraging multi-modal techniques and advanced generative prior, SUPIR marks a significant advance in intelligent and realistic image restoration. As a pivotal catalyst within SUPIR, model scaling dramatically enhances its capabilities and demonstrates new potential for image restoration. We collect a dataset comprising 20 million high-resolution, high-quality images for model training, each enriched with descriptive text annotations. SUPIR provides the capability to restore images guided by textual prompts, broadening its application scope and potential. Moreover, we introduce negative-quality prompts to further improve perceptual quality. We also develop a restoration-guided sampling method to suppress the fidelity issue encountered in generative-based restoration. Experiments demonstrate SUPIR's exceptional restoration effects and its novel capacity to manipulate restoration through textual prompts.
Code (0)
등록된 구현이 없습니다.
Tasks
DescriptiveImage RestorationSimilar Papers 제목 키워드 기반
Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images
This paper introduces the Global-Local Image Perceptual Score (GLIPS), an image metric designed to assess the photorealistic image quality of AI-generated images with a high degree of alignment to human visual perception…
Image GenerationMS-SSIMSSIMCaricatureShop: Personalized and Photorealistic Caricature Sketching
In this paper, we propose the first sketching system for interactively personalized and photorealistic face caricaturing. Input an image of a human face, the users can create caricature photos by manipulating its facial …
CaricatureFace ModelRaising The Limit Of Image Rescaling Using Auxiliary Encoding
Normalizing flow models using invertible neural networks (INN) have been widely investigated for successful generative image super-resolution (SR) by learning the transformation between the normal distribution of latent …
Image RescalingImage Super-ResolutionSuper-ResolutionLearning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction
Image downscaling is critical for efficient storage and transmission of high-resolution (HR) images. Existing learning-based methods focus on performing downscaling within the sRGB domain, which typically suffers from bl…
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture de…
Generative Adversarial NetworkImage Super-ResolutionSuper-Resolution