AI Paper Atlas

Research map / Benchmarks / KonIQ-10k

KonIQ-10k leaderboard

20 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on KonIQ-10k. Best SRCC: 0.938 (CMPA + RPD (Ours), ICML 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.

KonIQ-10k · SRCC

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

#SRCC ↑MethodPaperTopic
10.938CMPA + RPD (Ours)
CLIP
Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA
ICML 2026 · Table 1
Cross-modal learning
20.934QCN
ResNet50
Blind Image Quality Assessment Based on Geometric Order Learning
CVPR 2024 · Table 1
Autoregressive and latent generation
30.932LoDa
ViT-B + ResNet50
Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
CVPR 2024 · Table 1
Autoregressive and latent generation
40.931Compare2Score
mPLUG-Owl2
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
NeurIPS 2024 · Table: Performance comparison
Autoregressive and latent generation
50.9271QPT-ResNet50
ResNet50
Quality-Aware Pre-Trained Models for Blind Image Quality Assessment
CVPR 2023 · Table: Performance of existing
Image restoration
60.927PPA-T
CLIP-B/16
Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment
CVPR 2026 · Table 5
Multimodal LLMs
70.92DEFNetMultitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment
AAAI 2026 · Table 1
Image restoration
80.919VILA-R
CoCa-Base
VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining
CVPR 2023 · Table: Results on KonIQ-10k
CLIP and zero-shot
90.919LIQE
CLIP
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
CVPR 2023 · Table 1
Human and embodied modeling
100.906Ours
ResNet-50
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
CVPR 2020 · Table 1
Image restoration
6 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

KonIQ-10k · PLCC

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

#PLCC ↑MethodPaperTopic
10.944Dinov2-small + Charm
Dinov2-small
Charm: The Missing Piece in ViT Fine-Tuning for Image Aesthetic Assessment
CVPR 2025 · Table 1
Pruning and efficient tuning
20.944LoDa
ViT-B + ResNet50
Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
CVPR 2024 · Table 1
Autoregressive and latent generation
30.9413QPT-ResNet50
ResNet50
Quality-Aware Pre-Trained Models for Blind Image Quality Assessment
CVPR 2023 · Table: Performance of existing
Image restoration
40.939Compare2Score
mPLUG-Owl2
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
NeurIPS 2024 · Table: Performance comparison
Autoregressive and latent generation
50.932VILA-R
CoCa-Base
VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining
CVPR 2023 · Table: Results on KonIQ-10k
CLIP and zero-shot
60.918CIS
ResNet18
Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference
ICML 2024 · Table 2
Causal discovery
70.917Ours
ResNet-50
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
CVPR 2020 · Table 1
Image restoration
80.909CLIP-IQA+
CLIP ResNet-50
Exploring CLIP for Assessing the Look and Feel of Images
AAAI 2023 · Table 1
CLIP and zero-shot
90.908LIQE
CLIP
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
CVPR 2023 · Table 1
Human and embodied modeling
100.901DEFNetMultitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment
AAAI 2026 · Table 1
Image restoration
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.