UltraHR-100K：透過大規模高品質數據集提升超高解析度影像合成技術

摘要

超高分辨率（UHR）文本到图像（T2I）生成技术已取得显著进展，但依然面临两大核心挑战：其一，缺乏大规模高质量的UHR T2I数据集；其二，针对UHR场景下细粒度细节合成的定制化训练策略研究不足。为解决首个挑战，我们推出包含10万张高分辨率图像的UltraHR-100K数据集，该数据集配备丰富标注文本，涵盖多样化内容并具备卓越视觉保真度。每张图像分辨率均超过3K，并基于细节丰富度、内容复杂度与美学质量进行严格筛选。针对第二个挑战，我们提出一种频率感知的后训练方法，可增强T2I扩散模型的精细细节生成能力。具体而言，我们设计了（i）面向细节的时序步长采样（DOTS）机制，将学习重点集中于细节关键的降噪步骤；（ii）软加权频率正则化（SWFR）方法，通过离散傅里叶变换（DFT）对频率分量进行柔性约束，促进高频细节保留。在我们提出的UltraHR-eval4K基准测试上的大量实验表明，该方法能显著提升UHR图像生成的细粒度细节质量与整体保真度。相关代码已发布于https://github.com/NJU-PCALab/UltraHR-100k。

English

Ultra-high-resolution (UHR) text-to-image (T2I) generation has seen notable progress. However, two key challenges remain : 1) the absence of a large-scale high-quality UHR T2I dataset, and (2) the neglect of tailored training strategies for fine-grained detail synthesis in UHR scenarios. To tackle the first challenge, we introduce UltraHR-100K, a high-quality dataset of 100K UHR images with rich captions, offering diverse content and strong visual fidelity. Each image exceeds 3K resolution and is rigorously curated based on detail richness, content complexity, and aesthetic quality. To tackle the second challenge, we propose a frequency-aware post-training method that enhances fine-detail generation in T2I diffusion models. Specifically, we design (i) Detail-Oriented Timestep Sampling (DOTS) to focus learning on detail-critical denoising steps, and (ii) Soft-Weighting Frequency Regularization (SWFR), which leverages Discrete Fourier Transform (DFT) to softly constrain frequency components, encouraging high-frequency detail preservation. Extensive experiments on our proposed UltraHR-eval4K benchmarks demonstrate that our approach significantly improves the fine-grained detail quality and overall fidelity of UHR image generation. The code is available at https://github.com/NJU-PCALab/UltraHR-100k{here}.

UltraHR-100K：透過大規模高品質數據集提升超高解析度影像合成技術

UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

摘要

Support