# Low-light raw denoising on ELD Sony (test)

Source: [Low-light raw denoising on ELD Sony (test)](<https://www.sota2.com/research/sota/low-light-raw-denoising-on-eld-sony-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:55:52.618Z

Evaluation of low-light raw image denoising performance using PSNR and SSIM on the test split of the ELD Sony dataset.

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 | Low-light raw denoising |
| Dataset (including any stated split) | ELD Sony (test) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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](<https://www.sota2.com/research/sota/low-light-raw-denoising-on-eld-sony-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/low-light-raw-denoising-on-eld-sony-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| ELD | 45.06 | Not recorded | 68fa70f01e209131cea4e251 |
| FTD | 44.95 | Not recorded | 68fa70f01e209131cea4e251 |
| Paired data | 43.8 | Not recorded | 68fa70f01e209131cea4e251 |
| FTD | 43.32 | Not recorded | 68fa70f01e209131cea4e251 |
| ELD | 43.21 | Not recorded | 68fa70f01e209131cea4e251 |
| Paired data | 41.54 | Not recorded | 68fa70f01e209131cea4e251 |
| Poisson-Gaussian | 39.46 | Not recorded | 68fa70f01e209131cea4e251 |
| Noise Flow | 38.68 | Not recorded | 68fa70f01e209131cea4e251 |
| Noise Flow | 36.3 | Not recorded | 68fa70f01e209131cea4e251 |
| Poisson-Gaussian | 33.81 | Not recorded | 68fa70f01e209131cea4e251 |

### ELD

PSNR: 45.06. Result ID: 69917fe43a6c314849089033.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67531e209131cea157bc.md>)

[Implementation](<https://github.com/Vandermode/NoiseModel>)

Recorded evaluation configuration: {"Ratio":"x100","Method category":"Real-noise-based"}. This record does not assert independent reproduction.

### FTD

PSNR: 44.95. Result ID: 69917fe43a6c314849089039.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

Recorded evaluation configuration: {"Ratio":"x100","Method category":"DNN-based"}. This record does not assert independent reproduction.

### Paired data

PSNR: 43.8. Result ID: 69917fe43a6c314849089035.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

Recorded evaluation configuration: {"Ratio":"x100","Method category":"Real-noise-based"}. This record does not assert independent reproduction.

### FTD

PSNR: 43.32. Result ID: 69917fe43a6c31484908903a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

Recorded evaluation configuration: {"Ratio":"x200","Method category":"DNN-based"}. This record does not assert independent reproduction.

### ELD

PSNR: 43.21. Result ID: 69917fe43a6c314849089034.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67531e209131cea157bc.md>)

[Implementation](<https://github.com/Vandermode/NoiseModel>)

Recorded evaluation configuration: {"Ratio":"x200","Method category":"Real-noise-based"}. This record does not assert independent reproduction.

### Paired data

PSNR: 41.54. Result ID: 69917fe43a6c314849089036.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

Recorded evaluation configuration: {"Ratio":"x200","Method category":"Real-noise-based"}. This record does not assert independent reproduction.

### Poisson-Gaussian

PSNR: 39.46. Result ID: 69917fe43a6c314849089031.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

Recorded evaluation configuration: {"Ratio":"x100","Method category":"Physics-based"}. This record does not assert independent reproduction.

### Noise Flow

PSNR: 38.68. Result ID: 69917fe43a6c314849089037.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef04.md>)

[Implementation](<https://github.com/BorealisAI/noise_flow>)

Recorded evaluation configuration: {"Ratio":"x100","Method category":"DNN-based"}. This record does not assert independent reproduction.

### Noise Flow

PSNR: 36.3. Result ID: 69917fe43a6c314849089038.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef04.md>)

[Implementation](<https://github.com/BorealisAI/noise_flow>)

Recorded evaluation configuration: {"Ratio":"x200","Method category":"DNN-based"}. This record does not assert independent reproduction.

### Poisson-Gaussian

PSNR: 33.81. Result ID: 69917fe43a6c314849089032.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f01e209131cea4e251.md>)

Recorded evaluation configuration: {"Ratio":"x200","Method category":"Physics-based"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
