Shape-noise comparison between our CNN model (red squares) and FPFS (blue circles) as a function of image noise level. The highest noise level corresponds to the standard deviation expected for LSST 10 yr coadded i-band images with a magnitude cut m_cut = 24.5. While both methods achieve comparable shape noise at low noise levels, the CNN model shows a ∼10% reduction in shape noise in the high-noise regime, demonstrating the improved noise robustness and effective denoising capability of the ML-based approach.