Iterative Inference-time Scaling for Image Super-Resolution
Published:Dec 29, 2025 15:09
•1 min read
•ArXiv
Analysis
This paper addresses the challenge of balancing perceptual quality and structural fidelity in image super-resolution using diffusion models. It proposes a novel training-free framework, IAFS, that iteratively refines images and adaptively fuses frequency information. The key contribution is a method to improve both detail and structural accuracy, outperforming existing inference-time scaling methods.
Key Takeaways
Reference
“IAFS effectively resolves the perception-fidelity conflict, yielding consistently improved perceptual detail and structural accuracy, and outperforming existing inference-time scaling methods.”