KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models
Yongliang Wu, Zonghui Li, Xinting Hu, Xinyu Ye, Xianfang Zeng, Gang YU, Wenbo Zhu, Bernt Schiele
Abstract
Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing tasks remains under-explored. In this paper, We introduce KRIS-Bench (Knowledge-based Reasoning in Image-editing Systems Benchmark), a diagnostic benchmark designed to assess models through a cognitively informed lens. Drawing from educational theory, KRIS-Bench categorizes editing tasks across three foundational knowledge types: Factual, Conceptual, and Procedural. Based on this taxonomy, we design 22 representative tasks spanning 7 reasoning dimensions and release 1,267 high-quality annotated editing instances. To support fine-grained evaluation, we propose a comprehensive protocol that incorporates a novel Knowledge Plausibility metric, enhanced by knowledge hints and calibrated through human studies. Empirical results on nine state-of-the-art models reveal significant gaps in reasoning performance, highlighting the need for knowledge-centric benchmarks to advance the development of intelligent image editing systems.
BibTeX
@inproceedings{
wu2025krisbench,
title={{KRIS}-Bench: Benchmarking Next-Level Intelligent Image Editing Models},
author={Yongliang Wu and Zonghui Li and Xinting Hu and Xinyu Ye and Xianfang Zeng and Gang YU and Wenbo Zhu and Bernt Schiele and Ming-Hsuan Yang and Xu Yang},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2025},
url={https://openreview.net/forum?id=aWSh1Ec64T}
}