PixVerve:通过大规模高质量数据集将原生超高清图像生成推至100MP
PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset
AI总结:
本文提出PixVerve-95K数据集,通过精心设计的数据管道构建,包含95K张高分辨率图像和七维标注,用于推动超高清图像生成技术,通过三种训练方案将T2I基础模型扩展到100MP生成,并建立PixVerve-Bench评估协议。
摘要:
文本到图像(T2I)模型近年来在1K和2K分辨率方面取得了显著进展。随着对更好视觉体验的极端需求和成像技术的快速发展,超高清(UHR)图像生成的需求显著增长。然而,由于高分辨率内容的稀缺性和复杂性,UHR图像生成面临巨大挑战。在本文中,我们首先介绍了PixVerve-95K,一个高质量、开源的UHR T2I数据集,通过精心设计的数据管道构建,包含95K张图像,涵盖多样场景(每张图像的最小像素数为100M)和七维标注。基于我们的大规模图像-文本数据集,我们采取了开创性的步骤,将各种T2I基础模型扩展到原生100MP生成,采用三种训练方案。最后,利用传统度量标准和基于多模态大语言模型的评估,我们提出的PixVerve-Bench基准建立了涵盖视觉质量和语义对齐的全面评估协议。在我们的基准上的广泛实验结果和训练策略的建设性探索共同提供了对未来突破的宝贵见解。
英文摘要:
Text-to-Image (T2I) models have recently seen notable progress around 1K and 2K resolution. With the extreme desire for better visual experience and the rapid development of imaging technology, the demand for Ultra-High-Resolution (UHR) image generation has grown significantly. However, UHR image generation poses great challenges due to the scarcity and complexity of high-resolution content. In this paper, we first introduce PixVerve-95K, a high-quality, open-source UHR T2I dataset curated with a carefully designed data pipeline, which contains 95K images across diverse scenarios (each image has a minimum pixel-count of 100M) and seven-dimensional annotations. Based on our large-scale image-text dataset, we take a pioneering step to extend various T2I foundation models to native 100MP generation with three training schemes. Finally, leveraging both conventional metrics and multimodal large language model-based assessments, our proposed PixVerve-Bench benchmark establishes a comprehensive evaluation protocol for UHR images encompassing visual quality and semantic alignment. Extensive experimental results on our benchmark and the constructive exploration of training strategies collaboratively provide valuable insights for future breakthroughs.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。