AI Paper Atlas

Research map / Benchmarks / DIV2K

DIV2K leaderboard

52 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on DIV2K. Best PSNR (val): 29.35 (BUFF, AAAI 2025).

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.

DIV2K · PSNR (val)

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

#PSNR ↑MethodPaperTopic
129.35BUFF
SRDiff
BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution
AAAI 2025 · Table 1
Super-resolution
229.079AESOP (RRDB)
RRDB
Auto-Encoded Supervision for Perceptual Image Super-Resolution
CVPR 2025 · Table 1
Super-resolution
328.819RRDB+LDL (DF2K training)
RRDB
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
CVPR 2022 · Table 1
Super-resolution
427.35BiMaCoSR
SinSR
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
ICML 2025 · Table 1
Quantization
526.0139ViDiT-Q W4A8
InfDiT
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
ICLR 2025 · InfDiT super-resolution table
Fast diffusion sampling
625.262LinearSRLinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
ICLR 2026 · Table 1
Super-resolution
725.11PassionSR W8A8
OSEDiff
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
CVPR 2025 · Table 2
Super-resolution
824.72SRSR-SeeSR-s50
SeeSR-s50
SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
NeurIPS 2025 · Table 1
Super-resolution
924.25AdaDiffSR
Stable Diffusion 2.1-base
AdaDiffSR: Adaptive Region-aware Dynamic acceleration Diffusion Model for Real-World Image Super-Resolution
ECCV 2024 · Table 1
Super-resolution
1024.23TVT-s1
SD 2.1-base
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
ICCV 2025 · Table 2
Super-resolution
20 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

DIV2K · LPIPS (val)

20 papers, each with its best reported number for its own method; lower is better.

10 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

DIV2K · CLIPIQA (val)

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

7 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

DIV2K · MUSIQ (val)

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

5 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

DIV2K · PSNR

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

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

DIV2K · MANIQA (val)

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

1 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.