Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution

TL;DR

This paper introduces IAFS, a training-free inference framework for image super-resolution that balances perceptual quality and structural fidelity through iterative refinement and adaptive frequency fusion.

Contribution

It proposes a novel inference-time scaling method that jointly uses iterative correction and frequency-aware particle fusion without additional training.

Findings

IAFS improves perceptual detail and structural accuracy in super-resolution images.

It outperforms existing inference-time scaling methods across multiple diffusion models.

The framework effectively balances high-frequency perceptual cues with low-frequency structural information.

Abstract

Diffusion models have become a leading paradigm for image super-resolution (SR), but existing methods struggle to guarantee both the high-frequency perceptual quality and the low-frequency structural fidelity of generated images. Although inference-time scaling can theoretically improve this trade-off by allocating more computation, existing strategies remain suboptimal: reward-driven particle optimization often causes perceptual over-smoothing, while optimal-path search tends to lose structural consistency. To overcome these difficulties, we propose Iterative Diffusion Inference-Time Scaling with Adaptive Frequency Steering (IAFS), a training-free framework that jointly leverages iterative refinement and frequency-aware particle fusion. IAFS addresses the challenge of balancing perceptual quality and structural fidelity by progressively refining the generated image through iterative correction of structural deviations. Simultaneously, it ensures effective frequency fusion by adaptively integrating high-frequency perceptual cues with low-frequency structural information, allowing for a more accurate and balanced reconstruction across different image details. Extensive experiments across multiple diffusion-based SR models show that IAFS effectively resolves the perception-fidelity conflict, yielding consistently improved perceptual detail and structural accuracy, and outperforming existing inference-time scaling methods.