# LSD$\_2$ -- Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs Source: [LSD$\_2$ -- Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:34:00.401Z Authors: Janne Mustaniemi, Juho Kannala, Jiri Matas, Simo S\\"arkk\\"a, Janne Heikkil\\"a Published: 2018-11-23T14:13:33.000Z ## Abstract The paper addresses the problem of acquiring high-quality photographs with handheld smartphone cameras in low-light imaging conditions. We propose an approach based on capturing pairs of short and long exposure images in rapid succession and fusing them into a single high-quality photograph. Unlike existing methods, we take advantage of both images simultaneously and perform a joint denoising and deblurring using a convolutional neural network. A novel approach is introduced to generate realistic short-long exposure image pairs. The method produces good images in extremely challenging conditions and outperforms existing denoising and deblurring methods. It also enables exposure fusion in the presence of motion blur. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Dual-Exposure Image Reconstruction on REDS-LL](): Dual-Exposure Image Reconstruction; REDS-LL; Runtime (ms): 14. - [Low-light image enhancement on REDS LL](): Low-light Image Enhancement; REDS-LL; PSNR: 34.079. - [Low-light image enhancement on PIED](): Low-light Image Enhancement; PIED; PSNR: 28.965. ## Original sources and implementation [Original paper]() [PDF]()