# Gaussian Grayscale Image Denoising on Urban100 sigma=50 14 Source: [Gaussian Grayscale Image Denoising on Urban100 sigma=50 14]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:55:38.148Z Evaluation of Gaussian grayscale image denoising performance on the Urban100 dataset under specific conditions defined by 'sigma=50 14', reporting PSNR. 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. | Scope | Recorded value | | --- | --- | | Task | Gaussian grayscale image denoising | | Dataset (including any stated split) | Urban100 sigma=50 14 | | Metric | PSNR | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [PSNR](): Higher is better; unit: SCALAR. ## Recorded results | Method | PSNR | Result date | Report paper | | --- | --- | --- | --- | | Restormer-Local | 28.45 | Not recorded | 68fa6d351e209131cea386dc | | Restormer-Local | 28.41 | Not recorded | 68fa6d351e209131cea386dc | | Restormer | 28.33 | Not recorded | 68fa6d351e209131cea386dc | | Restormer | 28.29 | Not recorded | 68fa6d351e209131cea386dc | | SwinIR | 27.98 | Not recorded | 68fa6d351e209131cea386dc | | DAGL | 27.97 | Not recorded | 68fa6d351e209131cea386dc | | DRUNet | 27.96 | Not recorded | 68fa6d351e209131cea386dc | | RNAN | 27.65 | Not recorded | 68fa6d351e209131cea386dc | | DeamNet | 27.53 | Not recorded | 68fa6d351e209131cea386dc | | NLRN | 27.49 | Not recorded | 68fa6d351e209131cea386dc | | MWCNN | 27.42 | Not recorded | 68fa6d351e209131cea386dc | | FFDNet | 26.5 | Not recorded | 68fa6d351e209131cea386dc | | DnCNN | 26.35 | Not recorded | 68fa6d351e209131cea386dc | | IRCNN | 26.22 | Not recorded | 68fa6d351e209131cea386dc | ### Restormer-Local PSNR: 28.45. Result ID: 698f83b03a6c314849f9900f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. ### Restormer-Local PSNR: 28.41. Result ID: 698f83b03a6c314849f99017. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### Restormer PSNR: 28.33. Result ID: 698f83b03a6c314849f9900e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. ### Restormer PSNR: 28.29. Result ID: 698f83b03a6c314849f99016. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### SwinIR PSNR: 27.98. Result ID: 698f83b03a6c314849f99015. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### DAGL PSNR: 27.97. Result ID: 698f83b03a6c314849f99014. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### DRUNet PSNR: 27.96. Result ID: 698f83b03a6c314849f9900d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. ### RNAN PSNR: 27.65. Result ID: 698f83b03a6c314849f99012. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### DeamNet PSNR: 27.53. Result ID: 698f83b03a6c314849f99013. [Reporting paper]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### NLRN PSNR: 27.49. Result ID: 698f83b03a6c314849f99011. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### MWCNN PSNR: 27.42. Result ID: 698f83b03a6c314849f99010. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### FFDNet PSNR: 26.5. Result ID: 698f83b03a6c314849f9900b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. ### DnCNN PSNR: 26.35. Result ID: 698f83b03a6c314849f9900a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. ### IRCNN PSNR: 26.22. Result ID: 698f83b03a6c314849f9900c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.