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

ArXi:2512.23532v2 Announce Type: replace 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 computation, existing strategies remain suboptimal: reward-driven particle optimization often causes perceptual over-smoothing, while optimal-path search tends to lose structural consistency.