No Free Lunch for Synthetic Images under Data Scarcity Conditions

This preprint examines the limits and trade-offs of synthetic image generation when data are scarce, with implications for reliable model evaluation and augmentation.

Recommended citation: Galende, B. A., Almodovar, A., Apellaniz, P. A., Parras, J., Uribe, S., & Zazo, S. (2026). No Free Lunch for Synthetic Images under Data Scarcity Conditions. arXiv preprint arXiv:2606.07640.