AI Paper Atlas

Research map / Benchmarks / Set5

Set5 leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Set5. Best PSNR: 37.37 (Adder VDSR 4, CVPR 2021).

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.

Set5 · PSNR

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

#PSNR ↑MethodPaperTopic
137.37Adder VDSR 4
VDSR
AdderSR: Towards Energy Efficient Image Super-Resolution
CVPR 2021 · Table: Ablation study of the p
Super-resolution
233.75HAT-L-F
HAT-L
FIPER: Factorized Features for Robust Image Super-Resolution and Compression
NeurIPS 2025 · Table 1
Super-resolution
333.344KAgent (ExpSR-s4-F)4KAgent: Agentic Any Image to 4K Super-Resolution
NeurIPS 2025 · Table: Quantitative comparison
Super-resolution
433.103EnsIR
SwinIR, SRFormer, MambaIR
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
NeurIPS 2024 · Table 3
Image restoration
532.9INN-init
SRCNN 3x
Integral Neural Networks
CVPR 2023 · Table 1(b)
Pruning and efficient tuning
632.48Ours (self-similarity SR)
RCAN
Robust Reference-Based Super-Resolution With Similarity-Aware Deformable Convolution
CVPR 2020 · Table 2
Super-resolution
732.46Adaptive category attention
ATD-light
Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
CVPR 2024 · Table 2
Super-resolution
831.79AGD (PSNR-oriented)
ESRGAN
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
ICML 2020 · Table 8
GANs
931.78SwinIR + SFD
SwinIR
Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment
CVPR 2025 · Table 1
Super-resolution
1031.508WGSR (2-lvl)
RRDB
Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts
CVPR 2024 · Table 1
Super-resolution
4 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.