Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets

TL;DR

This paper comprehensively evaluates Nano Banana Pro's performance on 14 low-level vision tasks across 40 datasets, revealing its strengths in subjective quality but limitations in quantitative accuracy compared to specialist models.

Contribution

It provides the first extensive zero-shot benchmark of Nano Banana Pro on diverse low-level vision tasks, highlighting its potential and current limitations.

Findings

Nano Banana Pro excels in subjective visual quality.

It underperforms in reference-based quantitative metrics.

Generative stochasticity affects pixel-level consistency.

Abstract

The rapid evolution of text-to-image generation models has revolutionized visual content creation. While commercial products like Nano Banana Pro have garnered significant attention, their potential as generalist solvers for traditional low-level vision challenges remains largely underexplored. In this study, we investigate the critical question: Is Nano Banana Pro a Low-Level Vision All-Rounder? We conducted a comprehensive zero-shot evaluation across 14 distinct low-level tasks spanning 40 diverse datasets. By utilizing simple textual prompts without fine-tuning, we benchmarked Nano Banana Pro against state-of-the-art specialist models. Our extensive analysis reveals a distinct performance dichotomy: while \textbf{Nano Banana Pro demonstrates superior subjective visual quality}, often hallucinating plausible high-frequency details that surpass specialist models, it lags behind in traditional reference-based quantitative metrics. We attribute this discrepancy to the inherent stochasticity of generative models, which struggle to maintain the strict pixel-level consistency required by conventional metrics. This report identifies Nano Banana Pro as a capable zero-shot contender for low-level vision tasks, while highlighting that achieving the high fidelity of domain specialists remains a significant hurdle.