Datasets › SID
SID (See-in-the-Dark)
The See-in-the-Dark (SID) dataset contains 5094 raw short-exposure images, each with a corresponding long-exposure reference image. Images were captured using two cameras: Sony α7SII and Fujifilm X-T2.
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Image Denoising | SID x100 | LLD* PSNR (Raw) 43.36 | Physics-Guided ISO-Dependent Sensor Noise Modeling for... | happycaoyue/lld | 8 | Compare |
| Image Denoising | SID x300 | LLD* PSNR (Raw) 37.80 | Physics-Guided ISO-Dependent Sensor Noise Modeling for... | happycaoyue/lld | 8 | Compare |
| Low-Light Image Enhancement | SID | Retinexformer PSNR 24.44 | Retinexformer: One-stage Retinex-based Transformer for... | cmhungsteve/Awesome-Transformer-Attention +4 | 2 | Compare |
Papers archive 2025-07-28
9 shown of 9 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 155. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement | 5 | 1 | 12 Mar 2023 | ran 2 of 10 samples (8 unverified) |
| Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography | 1 | 4 | 1 Jan 2023 | not harvested |
| Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling | 1 | 2 | 13 Jul 2022 | not harvested |
| Dancing under the stars: video denoising in starlight | 0 | 2 | 8 Apr 2022 | not harvested |
| Rethinking Noise Synthesis and Modeling in Raw Denoising | 1 | 2 | 10 Oct 2021 | ran 1 of 1 samples (0 unverified) |
| Physics-based Noise Modeling for Extreme Low-light Photography | 2 | 2 | 4 Aug 2021 | ran 1 of 8 samples (7 unverified) |
| Seeing Motion in the Dark | 1 | 1 | 1 Oct 2019 | not harvested |
| Noise Flow: Noise Modeling with Conditional Normalizing Flows | 1 | 2 | 22 Aug 2019 | not harvested |
| Learning to See in the Dark | 19 | 2 | 4 May 2018 | ran 1 of 14 samples (13 unverified; 2 pointer-only for licence) |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- SID
- SID x300
- SID x100
3 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections