Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

TL;DR

Chain-of-Zoom (CoZ) enables extreme super-resolution by autoregressively decomposing scale magnification into manageable steps, guided by multi-scale-aware prompts and reinforcement learning for high-quality, large-scale image enlargement.

Contribution

The paper introduces CoZ, a scalable, model-agnostic framework that achieves beyond 256x super-resolution without retraining, using scale autoregression and preference-aligned prompts.

Findings

CoZ attains beyond 256x enlargement with high perceptual quality.

Using a standard 4x diffusion SR model, CoZ effectively decomposes large magnifications.

Multi-scale-aware prompts improve visual fidelity at high magnifications.

Abstract

Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collapse when asked to magnify far beyond that regime. We address this scalability bottleneck with Chain-of-Zoom (CoZ), a model-agnostic framework that factorizes SISR into an autoregressive chain of intermediate scale-states with multi-scale-aware prompts. CoZ repeatedly re-uses a backbone SR model, decomposing the conditional probability into tractable sub-problems to achieve extreme resolutions without additional training. Because visual cues diminish at high magnifications, we augment each zoom step with multi-scale-aware text prompts generated by a vision-language model (VLM). The prompt extractor itself is fine-tuned using Generalized Reward Policy Optimization (GRPO) with a critic VLM, aligning text guidance towards human preference. Experiments show that a standard 4x diffusion SR model wrapped in CoZ attains beyond 256x enlargement with high perceptual quality and fidelity. Project Page: https://bryanswkim.github.io/chain-of-zoom/.