RENOIR - A Dataset for Real Low-Light Image Noise Reduction
This addresses the issue for researchers and practitioners in computer vision by providing a more realistic benchmark for denoising, though it is incremental as it focuses on dataset creation and evaluation rather than a new method.
The authors tackled the problem of evaluating image denoising algorithms on real low-light noise by introducing the RENOIR dataset, which includes color images with natural noise and aligned low-noise counterparts, and showed that some algorithms that outperform BM3D on synthetic noise lag behind on this real dataset.
Image denoising algorithms are evaluated using images corrupted by artificial noise, which may lead to incorrect conclusions about their performances on real noise. In this paper we introduce a dataset of color images corrupted by natural noise due to low-light conditions, together with spatially and intensity-aligned low noise images of the same scenes. We also introduce a method for estimating the true noise level in our images, since even the low noise images contain small amounts of noise. We evaluate the accuracy of our noise estimation method on real and artificial noise, and investigate the Poisson-Gaussian noise model. Finally, we use our dataset to evaluate six denoising algorithms: Active Random Field, BM3D, Bilevel-MRF, Multi-Layer Perceptron, and two versions of NL-means. We show that while the Multi-Layer Perceptron, Bilevel-MRF, and NL-means with soft threshold outperform BM3D on gray images with synthetic noise, they lag behind on our dataset.