# Neural Camera Simulators Source: [Neural Camera Simulators]() Collection index: [llms.txt]() Data updated: 2025-12-24T15:59:47.165Z Authors: Hao Ouyang, Zifan Shi, Chenyang Lei, Ka Lung Law, Qifeng Chen Published: 2021-04-12T07:06:27.000Z ## Abstract We present a controllable camera simulator based on deep neural networks to synthesize raw image data under different camera settings, including exposure time, ISO, and aperture. The proposed simulator includes an exposure module that utilizes the principle of modern lens designs for correcting the luminance level. It also contains a noise module using the noise level function and an aperture module with adaptive attention to simulate the side effects on noise and defocus blur. To facilitate the learning of a simulator model, we collect a dataset of the 10,000 raw images of 450 scenes with different exposure settings. Quantitative experiments and qualitative comparisons show that our approach outperforms relevant baselines in raw data synthesize on multiple cameras. Furthermore, the camera simulator enables various applications, including large-aperture enhancement, HDR, auto exposure, and data augmentation for training local feature detectors. Our work represents the first attempt to simulate a camera sensor's behavior leveraging both the advantage of traditional raw sensor features and the power of data-driven deep learning. ## 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. - [Raw-to-raw translation on Nikon Z6 (test)](): Raw-to-raw translation; Nikon Z6 (test); PSNR: 36.1. - [Raw-to-raw translation on Canon 70D (test)](): Raw-to-raw translation; Canon 70D (test); PSNR: 34.28. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()