No-Reference Image Quality Assessment
53 papers with code • 5 benchmarks • 5 datasets
An Image Quality Assessment approach where no reference image information is available to the model. Sometimes referred to as Blind Image Quality Assessment (BIQA).
Latest papers
Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
To be specific, we present theoretical evidence showing that the magnitude of score changes is related to the $\ell_1$ norm of the model's gradient with respect to the input image.
Quality-Aware Image-Text Alignment for Real-World Image Quality Assessment
In particular, we introduce a quality-aware image-text alignment strategy to make CLIP generate representations that correlate with the inherent quality of the images.
Transformer-based No-Reference Image Quality Assessment via Supervised Contrastive Learning
We first train a model on a large-scale synthetic dataset by SCL (no image subjective score is required) to extract degradation features of images with various distortion types and levels.
Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality Assessment
No-reference (NR) image quality assessment (IQA) is an important tool in enhancing the user experience in diverse visual applications.
PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Images
Although previous work has established several human perception-based AIGC image quality assessment (AIGCIQA) databases for text-generated images, the AI image generation technology includes scenarios like text-to-image and image-to-image, and assessing only the images generated by text-to-image models is insufficient.
VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data
In this work, we for the first time, present a video compression-based degradation model to synthesize low-resolution image data in the blind SISR task.
ARNIQA: Learning Distortion Manifold for Image Quality Assessment
In this work, we propose a self-supervised approach named ARNIQA (leArning distoRtion maNifold for Image Quality Assessment) for modeling the image distortion manifold to obtain quality representations in an intrinsic manner.
You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment
When our proposed model is independently trained on NR or FR IQA tasks, it outperforms existing models and achieves state-of-the-art performance.
On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement
We tackle this issue by examining the spectral discriminators in the context of perceptual image super-resolution (i. e., GAN-based SR), as SR image quality is susceptible to spectral changes.
Self2Self+: Single-Image Denoising with Self-Supervised Learning and Image Quality Assessment Loss
To improve the feasibility of denoising procedures, in this study, we proposed a single-image self-supervised learning method in which only the noisy input image is used for network training.