AI Paper Atlas

Research map / Benchmarks / KADID

KADID leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on KADID. Best PLCC: 0.972 (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.

KADID · PLCC

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

#PLCC ↑MethodPaperTopic
10.972BWAFDA
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
20.961LGDM-ψSDv1.5
Stable Diffusion 1.5
LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations
ICML 2025 · Table 2
Fast diffusion sampling
30.945DSMix (Ours)
ResNet-50
DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment
ECCV 2024 · Table 2
Autoregressive and latent generation
40.94SHDIQA
ViT-S
Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment
CVPR 2025 · Table 1
Image restoration
50.935PFD-IQA
ViT-B/16
Feature Denoising Diffusion Model for Blind Image Quality Assessment
AAAI 2025 · Table 1
Image restoration
60.919CSIQA
ViT-S
Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment
ICML 2024 · Table 1
Autoregressive and latent generation
70.906QFM-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
80.905Our-EffNet
EfficientNet
Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference
CVPR 2025 · Table 1
Causal discovery
90.887DEIQT
ViT-S
Data-Efficient Image Quality Assessment with Attention-Panel Decoder
AAAI 2023 · Table 1
Autoregressive and latent generation
100.745VisualScore (Ours)
Qwen2.5-VL-7B
VisualScore: Learning Holistic Visual Quality Scores via Multi-Task Reasoning
ICML 2026 · Table 1
Text-to-image diffusion
3 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

KADID · SRCC

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

#SRCC ↑MethodPaperTopic
10.97BWAFDA
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
20.958LGDM-ψSDv1.5
Stable Diffusion 1.5
LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations
ICML 2025 · Table 2
Fast diffusion sampling
30.943DSMix (Ours)
ResNet-50
DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment
ECCV 2024 · Table 2
Autoregressive and latent generation
40.939DepictQA
LLaMA-2-chat-7B
Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models
ECCV 2024 · Table 2b
Multimodal LLMs
50.937SHDIQA
ViT-S
Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment
CVPR 2025 · Table 1
Image restoration
60.931PFD-IQA
ViT-B/16
Feature Denoising Diffusion Model for Blind Image Quality Assessment
AAAI 2025 · Table 1
Image restoration
70.919CSIQA
ViT-S
Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment
ICML 2024 · Table 1
Autoregressive and latent generation
80.907Our-EffNet
EfficientNet
Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference
CVPR 2025 · Table 1
Causal discovery
90.906QFM-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
100.901Q-Probe (ours)
Qwen2.5-VL-7B
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
NeurIPS 2026 · Table 1
Multimodal LLMs
2 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.