Saved in:
Bibliographic Details
Main Authors: Sun, Weixiong, Yin, Xiang, Dong, Chao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03061
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918497697660928
author Sun, Weixiong
Yin, Xiang
Dong, Chao
author_facet Sun, Weixiong
Yin, Xiang
Dong, Chao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03061
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks
Sun, Weixiong
Yin, Xiang
Dong, Chao
Computer Vision and Pattern Recognition
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.
title Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.03061