VINS-120K：基于大规模数据集的超高清图像编辑
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
针对超高清图像编辑中高频纹理细节难以建模的问题，提出高频感知的后适配策略，可将预训练的非高清编辑模型扩展到超高清域，为高分辨率生成与编辑提供可复用的微调思路。
原文依据 a high-frequency-aware post-adaptation strategy to extend pretrained non-high-resolution models to the UHR regime
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论直接编辑超高清（UHR）图像具有重要价值但尚未被充分探索，主要原因是缺乏高质量数据以及难以对高频纹理细节进行建模。我们提出 VINS-120K，这是首个面向基于指令的超高清图像编辑的大规模数据集，包含 12 万组精心筛选的指令、输入图像和编辑图像三元组。每张图像均超过 4K 分辨率（≥4096×4096），并通过严格的多阶段流程进行过滤，以确保视觉质量、指令对齐和美学保真度。基于 VINS-120K，我们进一步提出一种高频感知的后适配策略，将预训练的非高清模型扩展到超高清域。我们还提出 VINS-4KEval，一个涵盖多种编辑类型的基准，以促进超高清设置下的一致评估。实验证实，我们的工作提升了超高清图像编辑中的细粒度细节合成和纹理真实感。
英文原文摘要 949 字符
Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in modeling high-frequency texture details. We introduce VINS-120K, the first large-scale dataset for instruction-based UHR image editing, comprising 120K carefully curated triplets of instruction, input image, and edited image. Each image exceeds 4K resolution (\geq4096x4096) and is filtered through a rigorous multi-stage pipeline to ensure visual quality, instruction alignment, and aesthetic fidelity. Built on VINS-120K, we further develop a high-frequency-aware post-adaptation strategy to extend pretrained non-high-resolution models to the UHR regime. We also present VINS-4KEval, a benchmark covering diverse editing types, to facilitate consistent evaluation in UHR settings. Experiments confirm that our work improves fine-grained detail synthesis and texture realism in UHR image editing.