| IFCSR: Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-Resolution | | 30.86 | 42.32 | 0.3179 | 0.338 | 0.8472 | IFCSR | 2026-06-03 |
| GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution | | 29.85 | 57.14 | 0.2640 | 0.5230 | 0.8078 | GuideSR | 2025-05-01 |
| DACESR: Degradation-Aware Conditional Embedding for Real-World Image Super-Resolution | ✓ Link | 29.74 | | 0.2803 | | | DACESR | 2026-02-27 |
| Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization | ✓ Link | 29.0948 | 34.6331 | 0.2893 | | 0.7937 | PASD | 2023-08-28 |
| FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution | ✓ Link | 28.90 | 65.7820 | 0.2836 | 0.6239 | 0.7907 | FiDeSR-1s | 2026-03-03 |
| Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution | | 28.77 | 64.83 | 0.2896 | 0.6043 | 0.7973 | ASDSR | 2026-09-08 |
| AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution | | 28.54 | 63.83 | 0.3184 | 0.4685 | 0.7682 | AlignVAR | 2026-02-28 |
| TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution | | 28.54 | 62.7 | 0.2722 | 0.5582 | 0.7876 | TEASR (extra data) | 2026-06-15 |
| Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach | ✓ Link | 28.31 | 66.11 | 0.2960 | 0.6156 | 0.7804 | PiSA-SR-S1 | 2024-12-04 |
| AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution | ✓ Link | 28.2226 | | 0.2969 | | 0.7845 | AdaBridge-SR-S1 | 2026-09-08 |
| SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution | ✓ Link | 28.17 | 64.93 | 0.3189 | 0.6042 | 0.7691 | SeeSR | 2023-11-27 |
| Visual Autoregressive Modeling for Image Super-Resolution | ✓ Link | 28.16 | 68.15 | 0.3541 | 0.5362 | 0.7652 | VARSR | 2025-01-31 |
| DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution | | 28.141 | 68.732 | 0.3531 | 0.6515 | | DNF-SR | 2026-06-03 |
| One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution | ✓ Link | 28.14 | 62.86 | 0.2592 | 0.6227 | 0.7736 | ODTSR | 2025-11-21 |
| Exploiting Diffusion Prior for Real-World Image Super-Resolution | ✓ Link | 28.03 | 58.51 | 0.3284 | | 0.7536 | StableSR | 2023-05-11 |
| One-Step Effective Diffusion Network for Real-World Image Super-Resolution | | 27.92 | 64.65 | 0.2968 | 0.5899 | 0.7835 | OSEDiff-s1 | 2024-10-24 |
| TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution | ✓ Link | 27.77 | 66.62 | 0.2967 | 0.5874 | 0.7559 | TSD-SR | 2024-11-27 |
| Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution | | 27.53 | | | | | RRDB + Implicit Adaptive Dropout | 2025-06-15 |
| TinySR: Pruning Diffusion for Real-World Image Super-Resolution | | 27.48 | 65.36 | 0.3116 | 0.5804 | 0.7459 | TinySR | 2025-08-24 |
| XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution | ✓ Link | 26.62 | 67.84 | 0.3864 | 0.5713 | 0.7220 | XPSR | 2024-03-08 |
| AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation | ✓ Link | 26.09 | 68.16 | | 0.6034 | 0.7036 | AddSR | 2024-04-02 |
| One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation | ✓ Link | 25.92 | 37.82 | 0.3418 | 0.5310 | 0.7592 | FluxSR-s1 | 2025-02-04 |
| Disentangled Textual Priors for Diffusion-based Image Super-Resolution | ✓ Link | 25.83 | 69.24 | 0.3953 | 0.6011 | 0.7005 | DTPSR | 2026-03-08 |
| Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution | ✓ Link | 25.77 | 68.36 | 0.2874 | 0.6067 | 0.7356 | ASASR | 2026-05-22 |
| DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior | ✓ Link | 25.6238 | 69.8821 | 0.2350 | 0.3530 | 0.6544 | DiffBIR | 2023-08-29 |
| LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution | | 25.235 | 69.073 | 0.359 | 0.510 | 0.719 | LinearSR | 2025-10-09 |
| Learning to Corrupt for Better Restoration | | 24.605 | 65.676 | | 0.547 | 0.724 | IAC-IR | 2026-09-08 |
| VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution | | 24.31 | 69.49 | 0.3584 | 0.5638 | 0.6894 | VARestorer-1 | 2026-04-23 |
| Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning | | | 55.66 | 0.292 | | | Edge-SD-SR | 2024-12-09 |
| DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution | ✓ Link | | 64.950 | 0.365 | 0.627 | | DiT4SR | 2025-03-30 |
| Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models | | | 71.82 | | 0.6492 | | ResFlow-Tuner | 2026-03-23 |
| Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment | ✓ Link | | 71.48 | 0.315 | 0.483 | | NADB | 2026-05-27 |
| TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution | | | 66.365 | 0.3372 | 0.6312 | | TUDSR-S | 2026-06-03 |
| OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution | ✓ Link | | | 0.182 | | | OracleZoom | 2026-09-06 |
| AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution | ✓ Link | | 65.3485 | | 0.6436 | | AdaBridge-SR-S2 | 2026-09-08 |