Exploring CLIP for Assessing the Look and Feel of Images

  title={Exploring CLIP for Assessing the Look and Feel of Images},
  author={Jianyi Wang and Kelvin C. K. Chan and Chen Change Loy},
. Measuring the perception of visual content is a long-standing problem in computer vision. Many mathematical models have been devel-oped to evaluate the look or quality of an image. Despite the effectiveness of such tools in quantifying degradations such as noise and blurriness lev-els, such quantification is loosely coupled with human language. When it comes to more abstract perception about the feel of visual content, existing methods can only rely on supervised models that are explicitly… 

RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions

Inspired by crowdsourced editing strategies, this work curated intuitive text features, such as the number and concreteness of nouns, and trained a proxy model to analyze the feature effects on the AI-generated image.

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

The rapid increase in user-generated-content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still



PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference

A new learning-based method that is the first to predict perceptual image error like human observers, and significantly outperforms existing algorithms, beating the state-of-the-art by almost 3× on the authors' test set in terms of binary error rate, while also generalizing to new kinds of distortions, unlike previous learning- based methods.

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

It is indicated that existing IQA methods cannot fairly evaluate GAN-based IR algorithms, and a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) is contributed, which includes the results of GAn-based methods, which are missing in previous datasets.

Most apparent distortion: full-reference image quality assessment and the role of strategy

A quality assessment method [most apparent distortion (MAD)], which attempts to explicitly model these two separate strategies, local luminance and contrast masking and changes in the local statistics of spatial-frequency components are used to estimate appearance-based perceived distortion in low-quality images.

The Perception-Distortion Tradeoff

It is proved mathematically that distortion and perceptual quality are at odds with each other, and generative-adversarial-nets (GANs) provide a principled way to approach the perception-distortion bound.

Making a “Completely Blind” Image Quality Analyzer

This work has recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed, without any exposure to distorted images.

Massive Online Crowdsourced Study of Subjective and Objective Picture Quality

The LIVE In the Wild Image Quality Challenge Database is designed and created, which contains widely diverse authentic image distortions on a large number of images captured using a representative variety of modern mobile devices, and a new online crowdsourcing system is implemented, which is used to conduct a very large-scale, multi-month image quality assessment (IQA) subjective study.

VSI: A Visual Saliency-Induced Index for Perceptual Image Quality Assessment

Extensive experiments performed on four largescale benchmark databases demonstrate that the proposed IQA index VSI works better in terms of the prediction accuracy than all state-of-the-art IQA indices the authors can find while maintaining a moderate computational complexity.

Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems

This work uses eleven full-reference IQA models to train deep neural networks for four low-level vision tasks: denoising, deblurring, super-resolution, and compression, and uses subjective testing on the optimized images to rank the competing models in terms of their perceptual performance, elucidate their relative advantages and disadvantages.

Learning a No-Reference Quality Metric for Single-Image Super-Resolution

A Feature-Enriched Completely Blind Image Quality Evaluator

The proposed opinion-unaware BIQA method does not need any distorted sample images nor subjective quality scores for training, yet extensive experiments demonstrate its superior quality-prediction performance to the state-of-the-art opinion-aware BIZA methods.