Saved in:
Bibliographic Details
Main Authors: Liu, Lu, Duan, Huiyu, Zhu, Chenxin, Lu, Jintong, Jiang, Haoyun, Yang, Liu, Hu, Qiang, Zhai, Guangtao, Zhang, Xiaoyun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2606.02535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917556444463104
author Liu, Lu
Duan, Huiyu
Zhu, Chenxin
Lu, Jintong
Jiang, Haoyun
Yang, Liu
Hu, Qiang
Zhai, Guangtao
Zhang, Xiaoyun
author_facet Liu, Lu
Duan, Huiyu
Zhu, Chenxin
Lu, Jintong
Jiang, Haoyun
Yang, Liu
Hu, Qiang
Zhai, Guangtao
Zhang, Xiaoyun
contents Large-scale generative models have demonstrated remarkable capabilities across image generation and editing tasks. However, their performance in low-level vision tasks, which require pixel-wise control, remains insufficiently studied. To address this gap, we introduce \textbf{LL-Bench}, a comprehensive \textbf{Benchmark} for evaluating the capabilities of large-scale generative models on \textbf{L}ow-\textbf{L}evel vision tasks. The benchmark comprises 2,469 real-world degraded images covering 16 low-level degradation tasks, and 28,919 restored images produced by 10 state-of-the-art large-scale generative models and 21 conventional restoration models, which are annotated with 152,020 expert-level pairwise human preferences and 28,334 quality scores. Built upon LL-Bench, we present a systematic diagnosis that reveals the performance boundaries and unique failure modes of large-scale generative models across diverse low-level vision tasks, compared with conventional representative restoration approaches. Moreover, we investigate the effectiveness of current quality evaluation metrics on LL-Bench, which exhibit significant discrepancy with human ratings. To better align restored-image quality assessment with human preferences, we further propose \textbf{LL-Score}, an MLLM-based evaluator that captures both restoration quality and hallucination existence. Extensive experiments demonstrate that LL-score not only outperforms existing image quality assessment metrics, but also serves as a promising reward model for training generative models on low-level vision tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2606_02535
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
Liu, Lu
Duan, Huiyu
Zhu, Chenxin
Lu, Jintong
Jiang, Haoyun
Yang, Liu
Hu, Qiang
Zhai, Guangtao
Zhang, Xiaoyun
Computer Vision and Pattern Recognition
Large-scale generative models have demonstrated remarkable capabilities across image generation and editing tasks. However, their performance in low-level vision tasks, which require pixel-wise control, remains insufficiently studied. To address this gap, we introduce \textbf{LL-Bench}, a comprehensive \textbf{Benchmark} for evaluating the capabilities of large-scale generative models on \textbf{L}ow-\textbf{L}evel vision tasks. The benchmark comprises 2,469 real-world degraded images covering 16 low-level degradation tasks, and 28,919 restored images produced by 10 state-of-the-art large-scale generative models and 21 conventional restoration models, which are annotated with 152,020 expert-level pairwise human preferences and 28,334 quality scores. Built upon LL-Bench, we present a systematic diagnosis that reveals the performance boundaries and unique failure modes of large-scale generative models across diverse low-level vision tasks, compared with conventional representative restoration approaches. Moreover, we investigate the effectiveness of current quality evaluation metrics on LL-Bench, which exhibit significant discrepancy with human ratings. To better align restored-image quality assessment with human preferences, we further propose \textbf{LL-Score}, an MLLM-based evaluator that captures both restoration quality and hallucination existence. Extensive experiments demonstrate that LL-score not only outperforms existing image quality assessment metrics, but also serves as a promising reward model for training generative models on low-level vision tasks.
title LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2606.02535