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

arXiv:2505.18600v3 Announce Type: replace-cross 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/.

Related

• Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
• Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
• Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
• Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
• The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
• Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search

Source: arXiv cs.AI | 2026-04-13