RENOIR - A Benchmark Dataset for Real Noise Reduction Evaluation

In this paper we introduce a dataset of uncompressed color images taken with three digital cameras and exhibiting different levels of natural noise due to low-light conditions. For each scene there are on average two low-noise and two high noise images that are aligned at the pixel level both spatially and in intensity. The dataset contains over 100 scenes and more than 400 images, including both RAW formatted images and 8 bit BMP pixel and intensity aligned images. We also introduce a method for estimating the true noise level in each of our images. We use our dataset to analyze three current state of the art denoising algorithms: Active Random Field, BM3D, and Multi-Layer Perceptron. We found that BM3D obtains the best denoising results, however it is the slowest of the three methods with Active Random Field taking only a few seconds and MultiLater Perceptron and BM3D taking a few minutes to half an hour to denoise a 10 to 18 mega-pixel image.