# HRTEM Denoising on SFIN Dataset synthetic (test) Source: [HRTEM Denoising on SFIN Dataset synthetic (test)]() Collection index: [llms.txt]() Data updated: 2026-03-20T10:09:01.466Z Evaluation of High-Resolution Transmission Electron Microscopy (HRTEM) Denoising performance on the test split of the SFIN synthetic dataset, measured using PSNR and SSIM. 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 | HRTEM Denoising | | Dataset (including any stated split) | SFIN Dataset synthetic (test) | | Metric | PSNR | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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. - [SSIM](): Higher is better; unit: PERCENT. ## Recorded results | Method | PSNR | Result date | Report paper | | --- | --- | --- | --- | | SCGN | 38.99 | Not recorded | 69bcd4a30636e5bf4afc2b32 | | SFIN | 38.48 | Not recorded | 69bcd4a30636e5bf4afc2b32 | | HINT | 37.62 | Not recorded | 69bcd4a30636e5bf4afc2b32 | | AtomSegNet | 34.33 | Not recorded | 69bcd4a30636e5bf4afc2b32 | | Gaussian | 16.43 | Not recorded | 69bcd4a30636e5bf4afc2b32 | ### SCGN PSNR: 38.99. Result ID: 69bd1ca247f34ce924a7ca54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model type":"Supervised deep learning","Note":"Training datasets correspond to the testing datasets"}. This record does not assert independent reproduction. ### SFIN PSNR: 38.48. Result ID: 69bd1ca247f34ce924a7ca52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model type":"Supervised deep learning","Note":"Training datasets correspond to the testing datasets"}. This record does not assert independent reproduction. ### HINT PSNR: 37.62. Result ID: 69bd1ca247f34ce924a7ca53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model type":"Supervised deep learning","Note":"Training datasets correspond to the testing datasets"}. This record does not assert independent reproduction. ### AtomSegNet PSNR: 34.33. Result ID: 69bd1ca247f34ce924a7ca51. [Reporting paper]() Recorded evaluation configuration: {"Model type":"Supervised deep learning","Note":"Training datasets correspond to the testing datasets"}. This record does not assert independent reproduction. ### Gaussian PSNR: 16.43. Result ID: 69bd1ca247f34ce924a7ca50. [Reporting paper]() Recorded evaluation configuration: {"Training strategy":"Traditional filter","Note":"Training datasets correspond to the testing datasets"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.