Papers › Exploring CLIP for Assessing the Look and Feel of Images

Exploring CLIP for Assessing the Look and Feel of Images

25 Jul 2022arXiv:2207.12396archive 2025-07-28

Jianyi Wang, Kelvin C. K. Chan, Chen Change Loy

Measuring the perception of visual content is a long-standing problem in computer vision. Many mathematical models have been developed to evaluate the look or quality of an image. Despite the effectiveness of such tools in quantifying degradations such as noise and blurriness levels, 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 trained with labeled data collected via laborious user study. In this paper, we go beyond the conventional paradigms by exploring the rich visual language prior encapsulated in Contrastive Language-Image Pre-training (CLIP) models for assessing both the quality perception (look) and abstract perception (feel) of images in a zero-shot manner. In particular, we discuss effective prompt designs and show an effective prompt pairing strategy to harness the prior. We also provide extensive experiments on controlled datasets and Image Quality Assessment (IQA) benchmarks. Our results show that CLIP captures meaningful priors that generalize well to different perceptual assessments. Code is avaliable at https://github.com/IceClear/CLIP-IQA.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

iceclear/clip-iqa officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Quality AssessmentNo-Reference Image Quality AssessmentVideo Quality Assessment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
No-Reference Image Quality Assessment UHD-IQA CLIP-IQA+ PLCC 0.709 #3 of 7 Archive leaderboard report
No-Reference Image Quality Assessment UHD-IQA CLIP-IQA+ SRCC 0.747 #3 of 7 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ResNet50 KLCC 0.52628 #9 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ResNet50 PLCC 0.65154 #9 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ResNet50 SROCC 0.65713 #9 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ResNet50 Type NR #9 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA KLCC 0.49417 #17 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA PLCC 0.58944 #17 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA SROCC 0.60808 #17 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA Type NR #17 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ KLCC 0.69774 #25 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ PLCC 0.71808 #25 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ SROCC 0.56875 #25 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ Type NR #25 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ViT-L-14 KLCC 0.38794 #37 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ViT-L-14 PLCC 0.50379 #37 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ViT-L-14 SROCC 0.49881 #37 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset ClipIQA+ ViT-L-14 Type NR #37 of 60 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections