# Gaussian Grayscale Image Denoising on Urban100 (sigma=25) Source: [Gaussian Grayscale Image Denoising on Urban100 (sigma=25)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:55:38.131Z Evaluation of Gaussian grayscale image denoising performance on the Urban100 dataset, specifically reporting results for noise level sigma=25, measured using 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=25 14 | | Metric | PSNR | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | 31.55 | Not recorded | 68fa6d351e209131cea386dc | | Restormer-Local | 31.48 | Not recorded | 68fa6d351e209131cea386dc | | Restormer | 31.46 | Not recorded | 68fa6d351e209131cea386dc | | Restormer | 31.39 | Not recorded | 68fa6d351e209131cea386dc | | DAGL | 31.39 | Not recorded | 68fa6d351e209131cea386dc | | SwinIR | 31.3 | Not recorded | 68fa6d351e209131cea386dc | | DRUNet | 31.11 | Not recorded | 68fa6d351e209131cea386dc | | NLRN | 30.94 | Not recorded | 68fa6d351e209131cea386dc | | DeamNet | 30.85 | Not recorded | 68fa6d351e209131cea386dc | | MWCNN | 30.66 | Not recorded | 68fa6d351e209131cea386dc | | FFDNet | 29.9 | Not recorded | 68fa6d351e209131cea386dc | | DnCNN | 29.8 | Not recorded | 68fa6d351e209131cea386dc | | IRCNN | 29.8 | Not recorded | 68fa6d351e209131cea386dc | ### Restormer-Local PSNR: 31.55. Result ID: 698f83b03a6c314849f99009. [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-Local PSNR: 31.48. Result ID: 698f83b03a6c314849f99002. [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: 31.46. Result ID: 698f83b03a6c314849f99008. [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: 31.39. Result ID: 698f83b03a6c314849f99001. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. ### DAGL PSNR: 31.39. Result ID: 698f83b03a6c314849f99006. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### SwinIR PSNR: 31.3. Result ID: 698f83b03a6c314849f99007. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### DRUNet PSNR: 31.11. Result ID: 698f83b03a6c314849f99000. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Training":"single model for various noise levels"}. This record does not assert independent reproduction. ### NLRN PSNR: 30.94. Result ID: 698f83b03a6c314849f99004. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### DeamNet PSNR: 30.85. Result ID: 698f83b03a6c314849f99005. [Reporting paper]() Recorded evaluation configuration: {"Model Training":"separate model for each noise level"}. This record does not assert independent reproduction. ### MWCNN PSNR: 30.66. Result ID: 698f83b03a6c314849f99003. [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: 29.9. Result ID: 698f83b03a6c314849f98ffe. [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: 29.8. Result ID: 698f83b03a6c314849f98ffd. [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: 29.8. Result ID: 698f83b03a6c314849f98fff. [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.