Abstract:High-resolution datasets are essential for advancing super-resolution (SR) and text-to-image (T2I) diffusion research. However, current publicly available datasets lack both the native 4K resolution and the extensive scale necessary for training state-of-the-art models. To address this gap, we introduce a 4K Large Scale Dataset and Benchmark (4KLSDB), a large-scale, diverse dataset consisting of 129,484 carefully curated 4K resolution images spanning multiple categories such as nature, urban scenes, people, food, artwork, and CGI, alongside distinct validation and test sets containing 2,000 and 1,984 images respectively. Images were sourced from established open datasets including Photo Concept Bucket, Laion2B, and PD12M. 4KLSDB underwent rigorous multi-stage automated filtering and annotation pipelines involving both human annotators and Large Multimodal Models (LMMs) to ensure high aesthetic quality and dataset consistency. We demonstrate 4KLSDB's effectiveness by training representative super-resolution and diffusion models, observing significant improvements in performance on native 4K benchmarks. Comprehensive experiments illustrate a positive correlation between training on true 4K resolution data and improved fidelity in image restoration task, especially on 4K resolution. We provide the research community a valuable resource to drive progress toward genuinely high-fidelity image synthesis and restoration by providing 4KLSDB. Our project page is available at: this https URL.
| Comments: | Accepted to the DataCV Workshop at CVPR 2026; 10 pages, 4 figures, 7 tables; Our project page is available at: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2605.24762 [cs.CV] |
| (or arXiv:2605.24762v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24762 arXiv-issued DOI via DataCite (pending registration) |
From: Zihao Zhu [view email]
[v1]
Sat, 23 May 2026 22:49:04 UTC (38,540 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。