{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-physics-based-noise-formation-model-for","title":"A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising","arxiv_id":"2003.12751","date":"2020-03-28","proceeding":"CVPR 2020 6","authors":["Kaixuan Wei","Ying Fu","Jiaolong Yang","Hua Huang"],"abstract":"Lacking rich and realistic data, learned single image denoising algorithms generalize poorly to real raw images that do not resemble the data used for training. Although the problem can be alleviated by the heteroscedastic Gaussian model for noise synthesis, the noise sources caused by digital camera electronics are still largely overlooked, despite their significant effect on raw measurement, especially under extremely low-light condition. To address this issue, we present a highly accurate noise formation model based on the characteristics of CMOS photosensors, thereby enabling us to synthesize realistic samples that better match the physics of image formation process. Given the proposed noise model, we additionally propose a method to calibrate the noise parameters for available modern digital cameras, which is simple and reproducible for any new device. We systematically study the generalizability of a neural network trained with existing schemes, by introducing a new low-light denoising dataset that covers many modern digital cameras from diverse brands. Extensive empirical results collectively show that by utilizing our proposed noise formation model, a network can reach the capability as if it had been trained with rich real data, which demonstrates the effectiveness of our noise formation model.","url_abs":"https://arxiv.org/abs/2003.12751v2","url_pdf":"https://arxiv.org/pdf/2003.12751v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-physics-based-noise-formation-model-for","repo_url":"https://github.com/Vandermode/NoiseModel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[],"datasets_introduced":[{"slug":"eld","name":"ELD","full_name":"Extreme Low-light Denoising dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-denoising-on-eld-sonya7s2-x100","task":"Image Denoising","dataset":"ELD SonyA7S2 x100","model":"ELD","rank_in_archive_order":5,"of":9,"metrics":{"PSNR (Raw)":"45.45","SSIM (Raw)":"0.975"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-eld-sonya7s2-x200","task":"Image Denoising","dataset":"ELD SonyA7S2 x200","model":"ELD","rank_in_archive_order":5,"of":10,"metrics":{"PSNR (Raw)":"43.43","SSIM (Raw)":"0.954"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.12751","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}