# Low-light Raw Image Denoising on ELD Nikon D850 x200 (test)

Source: [Low-light Raw Image Denoising on ELD Nikon D850 x200 (test)](<https://www.sota2.com/research/sota/low-light-raw-image-denoising-on-eld-nikon-d850-x200-test>)

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

Data updated: 2026-02-26T05:55:29.180Z

Evaluation of low-light raw image denoising performance using PSNR and SSIM on the test split of the ELD Nikon D850 dataset (x200 magnification).

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 Image Denoising |
| Dataset (including any stated split) | ELD Nikon D850 x200 (test) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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-image-denoising-on-eld-nikon-d850-x200-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/low-light-raw-image-denoising-on-eld-nikon-d850-x200-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 40.36 | Not recorded | 68fa6a7d1e209131cea2892c |
| Paired data | 39.44 | Not recorded | 68fa6a7d1e209131cea2892c |
| Noise2Noise | 37.98 | Not recorded | 68fa6a7d1e209131cea2892c |
| Noiseflow | 37.61 | Not recorded | 68fa6a7d1e209131cea2892c |
| G+P | 37.26 | Not recorded | 68fa6a7d1e209131cea2892c |
| A-BM3D | 32.59 | Not recorded | 68fa6a7d1e209131cea2892c |
| BM3D | 31.36 | Not recorded | 68fa6a7d1e209131cea2892c |

### Ours

PSNR: 40.36. Result ID: 698e3b6cffc3901de09bda0d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

Recorded evaluation configuration: {"Training Data Category":"TRAINING WITH SYNTHETIC DATA"}. This record does not assert independent reproduction.

### Paired data

PSNR: 39.44. Result ID: 698e3b6cffc3901de09bda0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644b1e209131cea03c6a.md>)

Recorded evaluation configuration: {"Training Data Category":"TRAINING WITH REAL DATA"}. This record does not assert independent reproduction.

### Noise2Noise

PSNR: 37.98. Result ID: 698e3b6cffc3901de09bda09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64f91e209131cea0778f.md>)

Recorded evaluation configuration: {"Training Data Category":"TRAINING WITH REAL DATA"}. This record does not assert independent reproduction.

### Noiseflow

PSNR: 37.61. Result ID: 698e3b6cffc3901de09bda0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

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

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

Recorded evaluation configuration: {"Training Data Category":"TRAINING WITH SYNTHETIC DATA"}. This record does not assert independent reproduction.

### G+P

PSNR: 37.26. Result ID: 698e3b6cffc3901de09bda0c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

Recorded evaluation configuration: {"Training Data Category":"TRAINING WITH SYNTHETIC DATA"}. This record does not assert independent reproduction.

### A-BM3D

PSNR: 32.59. Result ID: 698e3b6cffc3901de09bda08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

Recorded evaluation configuration: {"Training Data Category":"NON-DEEP"}. This record does not assert independent reproduction.

### BM3D

PSNR: 31.36. Result ID: 698e3b6cffc3901de09bda07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2892c.md>)

Recorded evaluation configuration: {"Training Data Category":"NON-DEEP"}. This record does not assert independent reproduction.

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