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, Ming-Hsuan Yang, Xu Yang

Keywords: Image Editing, Knowledge-based Reasoning, Generative Model

TL;DR: We propose KRIS-Bench, a benchmark designed to evaluate knowledge-based reasoning in instruction-based image editing models.

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.

Dataset URL: https://huggingface.co/datasets/Liang0223/KRIS_Bench

Code URL: https://github.com/mercurystraw/Kris_Bench

Primary Area: Datasets & Benchmarks for applications in computer vision

Submission Number: 489