StableI2I: Spotting Unintended Changes in Image-to-Image Transition
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 accu...
| Authors | Jiayang Li, Shuo Cao, Xiaohui Li et al. |
|---|---|
| Primary category | cs.CV |
| Published | 6 May 2026 |
| Last updated at source | 6 May 2026 |
Models and datasets referencing this paper
- lijiayangCS/StableI2I_BenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.