2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition
This addresses the challenge of data acquisition for low-light denoising, making it more practical for real-world applications, though it is incremental in improving noise synthesis methods.
The paper tackles the problem of training denoisers for low-light images without requiring large paired datasets by proposing a noise synthesis method that uses only one noisy image and one dark frame per ISO setting, achieving state-of-the-art performance on multiple benchmarks.
Raw images taken in low-light conditions are very noisy due to low photon count and sensor noise. Learning-based denoisers have the potential to reconstruct high-quality images. For training, however, these denoisers require large paired datasets of clean and noisy images, which are difficult to collect. Noise synthesis is an alternative to large-scale data acquisition: given a clean image, we can synthesize a realistic noisy counterpart. In this work, we propose a general and practical noise synthesis method that requires only one single noisy image and one single dark frame per ISO setting. We represent signal-dependent noise with a Poisson distribution and introduce a Fourier-domain spectral sampling algorithm to accurately model signal-independent noise. The latter generates diverse noise realizations that maintain the spatial and statistical properties of real sensor noise. As opposed to competing approaches, our method neither relies on simplified parametric models nor on large sets of clean-noisy image pairs. Our synthesis method is not only accurate and practical, it also leads to state-of-the-art performances on multiple low-light denoising benchmarks.