StableI2I: Spotting Unintended Changes in Image-to-Image Transition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917463321477120 |
|---|---|
| author | Li, Jiayang Cao, Shuo Li, Xiaohui Zhang, Zhizhen Zhu, Kaiwen Duan, Yule Qiao, Yu Zhang, Jian Liu, Yihao |
| author_facet | Li, Jiayang Cao, Shuo Li, Xiaohui Zhang, Zhizhen Zhu, Kaiwen Duan, Yule Qiao, Yu Zhang, Jian Liu, Yihao |
| contents | In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. However, they largely fail to assess whether the output image preserves the semantic correspondence and spatial structure of the input image. To address this limitation, we propose StableI2I, a unified and dynamic evaluation framework that explicitly measures content fidelity and pre--post consistency across a wide range of I2I tasks without requiring reference images, including image editing and image restoration. In addition, we construct StableI2I-Bench, a benchmark designed to systematically evaluate the accuracy of MLLMs on such fidelity and consistency assessment tasks. Extensive experimental results demonstrate that StableI2I provides accurate, fine-grained, and interpretable evaluations of content fidelity and consistency, with strong correlations to human subjective judgments. Our framework serves as a practical and reliable evaluation tool for diagnosing content consistency and benchmarking model performance in real-world I2I systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04453 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StableI2I: Spotting Unintended Changes in Image-to-Image Transition Li, Jiayang Cao, Shuo Li, Xiaohui Zhang, Zhizhen Zhu, Kaiwen Duan, Yule Qiao, Yu Zhang, Jian Liu, Yihao Computer Vision and Pattern Recognition Artificial Intelligence In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. However, they largely fail to assess whether the output image preserves the semantic correspondence and spatial structure of the input image. To address this limitation, we propose StableI2I, a unified and dynamic evaluation framework that explicitly measures content fidelity and pre--post consistency across a wide range of I2I tasks without requiring reference images, including image editing and image restoration. In addition, we construct StableI2I-Bench, a benchmark designed to systematically evaluate the accuracy of MLLMs on such fidelity and consistency assessment tasks. Extensive experimental results demonstrate that StableI2I provides accurate, fine-grained, and interpretable evaluations of content fidelity and consistency, with strong correlations to human subjective judgments. Our framework serves as a practical and reliable evaluation tool for diagnosing content consistency and benchmarking model performance in real-world I2I systems. |
| title | StableI2I: Spotting Unintended Changes in Image-to-Image Transition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.04453 |