paper-with-me

Papers

Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild

2024-01-24 · CVPR 2024 1 · Fanghua Yu, Jinjin Gu, Zheyuan Li, JinFan Hu, Xiangtao Kong, Xintao Wang, Jingwen He, Yu Qiao, Chao Dong

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.

📄 PDF Abstract BibTeX arXiv:2401.13627

Code (0)

등록된 구현이 없습니다.

Tasks

DescriptiveImage Restoration

Similar Papers 제목 키워드 기반

Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images

2024-05-15 · Memoona Aziz, Umair Rehman, Muhammad Umair Danish, Katarina Grolinger

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-SSIMSSIM

CaricatureShop: Personalized and Photorealistic Caricature Sketching

2018-07-24 · Xiaoguang Han, Kangcheng Hou, Dong Du, Yuda Qiu 외

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 Model

Raising The Limit Of Image Rescaling Using Auxiliary Encoding

2023-03-12 · Chenzhong Yin, Zhihong Pan, Xin Zhou, Le Kang 외

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-Resolution

Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction

2025-07-31 · Yang Ren, Hai Jiang, Wei Li, Menglong Yang 외 arxiv

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

2016-09-15 · CVPR 2017 7 · Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero 외

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