通过分步缩放与文本引导，实现无需训练的超大倍率图像增强。
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
- 将超分辨率分解为多步缩放链，每步用多尺度提示增强细节。
- 4倍模型经改造后可实现256倍放大，保持高保真与视觉质量。
- 结合视觉语言模型生成提示，对齐人类偏好，适合图像修复场景。
当前单图超分辨率（SISR）模型在训练尺度下可生成逼真图像，但超出该范围时性能急剧下降。本文提出链式缩放（Chain-of-Zoom, CoZ）框架，将超分辨率分解为一系列中间尺度状态的自回归过程，并引入多尺度感知文本提示。该方法不依赖额外训练，仅复用基础超分模型，通过分步求解提升可扩展性。由于高倍放大时视觉线索减弱，每步缩放均结合由视觉语言模型生成的多尺度文本提示。提示提取器通过广义奖励策略优化（GRPO）与判别型视觉语言模型联合微调，使文本引导更符合人类偏好。实验表明，一个标准4倍扩散超分模型经CoZ封装后，可实现超过256倍的放大，且保持高感知质量和保真度。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。