为解决全局提示导致的细节缺失和误引导，提出分块提示框架提升图像视频超分辨率质量。
Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
- 为每个潜在图块生成专属提示，实现局部文本条件控制。
- 在高分辨率真实图像与视频上显著提升感知质量与保真度。
- 有效减少幻觉和块级伪影，适合追求高质量生成的开发者。
文本条件扩散模型通过将提示作为语义先验，推动了图像与视频超分辨率的发展，现代超分辨率流程通常依赖潜在空间分块以扩展至高分辨率。然而实践中使用单一全局提示与潜在分块结合，常引发提示误导：粗略的全局提示会遗漏局部细节（遗漏错误），并提供无关局部指导（误导错误），导致块级结果不佳。为此，我们提出 Tiled Prompts，一种统一的图像与视频超分辨率框架，为每个潜在图块生成专属提示，并在局部文本条件后验下执行超分辨率，以最小开销解决提示误导问题。在高分辨率真实图像与视频上的实验表明，分块提示在感知质量与保真度上带来一致提升，同时降低幻觉与块级伪影，优于全局提示基线。
原文摘要 · Abstract (English)
Text-conditioned diffusion models have advanced image and video super-resolution by using prompts as semantic priors, and modern super-resolution pipelines typically rely on latent tiling to scale to high resolutions. In practice, a single global caption is used with the latent tiling, often causing prompt misguidance. Specifically, a coarse global prompt often misses localized details (errors of omission) and provides locally irrelevant guidance (errors of commission) which leads to substandard results at the tile level. To solve this, we propose Tiled Prompts, a unified framework for image and video super-resolution that generates a tile-specific prompt for each latent tile and performs super-resolution under locally text-conditioned posteriors to resolve prompt misguidance with minimal overhead. Our experiments on high resolution real-world images and videos show that tiled prompts bring consistent gains in perceptual quality and fidelity, while reducing hallucinations and tile-level artifacts that can be found in global-prompt baselines. Project Page: https://bryanswkim.github.io/tiled-prompts/.
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。