English

Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks

Computer Vision and Pattern Recognition 2026-05-13 v2

Abstract

Recent advances in generative AI raise the question of whether general-purpose image editing models can serve as unified solutions for image restoration. We conduct a systematic evaluation of Nano Banana 2 across diverse scenes and degradations. Our results show that prompt design is critical, with concise prompts and explicit fidelity constraints achieving a better balance between reconstruction and perceptual quality. Nano Banana 2 achieves competitive full-reference performance and is consistently preferred in user studies, while showing strong generalization in challenging scenarios. However, we observe a gap between perceptual quality and restoration fidelity, as the model tends to produce visually rich results with over-enhanced details and inconsistencies. This issue is not well captured by existing IQA metrics or user studies. Overall, general-purpose models show promise as unified IR solvers from a perceptual perspective, but require improved controllability and fidelity-aware evaluation. Further comparisons and detailed analyses are available in our project repository: https://github.com/yxyuanxiao/NanoBanana2TestOnIR.

Keywords

Cite

@article{arxiv.2604.03061,
  title  = {Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks},
  author = {Weixiong Sun and Xiang Yin and Chao Dong},
  journal= {arXiv preprint arXiv:2604.03061},
  year   = {2026}
}

Comments

Accepted by CVPR 2026 Workshop AAVM