AI Paper Atlas

Research map / Benchmarks / CSIQ

CSIQ leaderboard

22 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CSIQ. Best SRCC: 0.983 (BWAFDA, ECCV 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CSIQ · SRCC

19 papers, each with its best reported number for its own method; higher is better.

#SRCC ↑MethodPaperTopic
10.983BWAFDA
ViT-S (DeiT-III)
BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment
ECCV 2026 · Table 1
Image restoration
20.977Ours(JSPL)Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
CVPR 2022 · Table: traditional dataset com
Semi-supervised learning
30.973Error-estimation fPieAPP: Perceptual Image-Error Assessment Through Pairwise Preference
CVPR 2018 · Table 3
Autoregressive and latent generation
40.967DEFNetMultitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment
AAAI 2026 · Table 1
Image restoration
50.964LGDM-ψSDv1.5
Stable Diffusion 1.5
LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations
ICML 2025 · Table 2
Fast diffusion sampling
60.962PPA-T
CLIP-B/16
Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment
CVPR 2026 · Table 5
Multimodal LLMs
70.962PFD-IQA
ViT-B/16
Feature Denoising Diffusion Model for Blind Image Quality Assessment
AAAI 2025 · Table 1
Image restoration
80.962SHDIQA
ViT-S
Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment
CVPR 2025 · Table 1
Image restoration
90.961DeepQADeep Learning of Human Visual Sensitivity in Image Quality Assessment Framework
CVPR 2017 · Table 1
Autoregressive and latent generation
100.96CSIQA
ViT-S
Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment
ICML 2024 · Table 1
Autoregressive and latent generation
9 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

CSIQ · PLCC

18 papers, each with its best reported number for its own method; higher is better.

#PLCC ↑MethodPaperTopic
10.988BWAFDA
ViT-S (DeiT-III)
BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment
ECCV 2026 · Table 1
Image restoration
20.981LGDM-ψSDv1.5
Stable Diffusion 1.5
LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations
ICML 2025 · Table 2
Fast diffusion sampling
30.975Error-estimation fPieAPP: Perceptual Image-Error Assessment Through Pairwise Preference
CVPR 2018 · Table 3
Autoregressive and latent generation
40.972PFD-IQA
ViT-B/16
Feature Denoising Diffusion Model for Blind Image Quality Assessment
AAAI 2025 · Table 1
Image restoration
50.972SHDIQA
ViT-S
Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment
CVPR 2025 · Table 1
Image restoration
60.972SaTQA
ViT-B/8
Transformer-Based No-Reference Image Quality Assessment via Supervised Contrastive Learning
AAAI 2024 · Main comparison table
Autoregressive and latent generation
70.97CSIQA
ViT-S
Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment
ICML 2024 · Table 1
Autoregressive and latent generation
80.97Ours(JSPL)Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
CVPR 2022 · Table: traditional dataset com
Semi-supervised learning
90.965QFM-IQM
ViT-S
Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
ICML 2024 · Table 1
Autoregressive and latent generation
100.965DeepQADeep Learning of Human Visual Sensitivity in Image Quality Assessment Framework
CVPR 2017 · Table 1
Autoregressive and latent generation
8 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.