UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture

caoshuo, lijiayang, Xiaohui Li, YuandongPu, Kaiwen Zhu, Yuanting Gao, Siqi Luo, Yi Xin, qinqi, Yu Zhou, Xiangyu Chen, Wenlong Zhang, Bin Fu, Yu Qiao, Yihao Liu

UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture: 27 upvotes on Hugging Face Daily Papers, #4 of 15 papers on 2025-12-29. Day-by-day upvote history.

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their ability to perceive perceptual-level image features remains limited. In this work, we present UniPercept-Bench, a unified framework for perceptual-level image understanding across three key domains: Aesthetics, Quality, Structure and Texture. We establish a hierarchical definition system and construct large-scale datasets to evaluate perceptual-level image understanding. Based on this foundation, we develop a strong baseline UniPercept trained via Domain-Adaptive Pre-Training and Task-Aligned RL, enabling robust generalization across both Visual Rating (VR) and Visual Question Answering (VQA) tasks. UniPercept outperforms existing MLLMs on perceptual-level image understanding and can serve as a plug-and-play reward model for text-to-image generation. This work defines Perceptual-Level Image Understanding in the era of MLLMs and, through the introduction of a comprehensive benchmark together with a strong baseline, provides a solid foundation for advancing perceptual-level multimodal image understanding.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.