Sensor-Physics-Driven Noise Modeling for Low-Light Imaging Using Adversarial Learning

High-fidelity imaging in extreme low light is challenged by ultra-low signal-to-noise ratios. We propose a hybrid noise modeling framework integrating physical priors with generative adversarial networks (GANs). The method simulates photon shot noise via Poisson distribution and incorporates readout, row, and quantization noise. A multi-layer perceptron (MLP) dynamically maps ISO levels to noise intensities in logarithmic space, followed by a residual U-Net for non-linear refinement. Results on the SID datasets show that our method outperforms state-of-the-art approaches in terms of Average Kullback–Leibler Divergence (AKLD). Denoising networks trained on our synthetic noise achieve performances comparable to those trained on real-world paired datasets.