unipercept
UniPercept-Bench
UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
Shuo Cao*,
Jiayang Li*,
Xiaohui Li,
Yuandong Pu,
Kaiwen Zhu,
Yuanting Gao,
Siqi Luo,
Yi Xin,
Qi Qin,
Yu Zhou,
Xiangyu Chen,
Wenlong Zhang,
Bin Fu,
Yu Qiao,
Yihao Liu†
University of Science and Technology of China
Shanghai AI Laboratory
Peking University
* Equal contribution
† Corresponding author
If you find this… See the full description on the dataset page: https://huggingface.co/datasets/Thunderbolt215215/UniPercept-Bench.UltraHR-100K-UniPercept
UltraHR-100K-UniPercept
🌟 Overview
UltraHR-100K-UniPercept is a perceptual annotation dataset based on UltraHR-100K. We have employed UniPercept, a state-of-the-art multimodal large language model (MLLM) specialized in perceptual image understanding, to provide comprehensive quality and aesthetic annotations for the original 100,000 ultra-high-resolution images.
This dataset focuses on providing fine-grained perceptual labels across three key dimensions:
IAA (Image… See the full description on the dataset page: https://huggingface.co/datasets/ModelMoe/UltraHR-100K-UniPercept.