# Neural ISP on Nighttime raw ISO 1600 (test)

Source: [Neural ISP on Nighttime raw ISO 1600 (test)](<https://www.sota2.com/research/sota/neural-isp-on-nighttime-raw-iso-1600-test>)

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

Data updated: 2026-02-26T05:55:36.294Z

Evaluation of Neural Image Signal Processing (ISP) performance on the Nighttime raw dataset captured at ISO 1600, using the test split, typically measured by 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 | Neural ISP |
| Dataset (including any stated split) | Nighttime raw ISO 1600 (test) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/neural-isp-on-nighttime-raw-iso-1600-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/neural-isp-on-nighttime-raw-iso-1600-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| Supervised | 39.74 | Not recorded | 68fa6cb31e209131cea3554d |
| Ours (90% Synthetic + 10% Real) | 39.04 | Not recorded | 68fa6cb31e209131cea3554d |
| Ours (95% Synthetic + 5% Real) | 38.32 | Not recorded | 68fa6cb31e209131cea3554d |
| Ours | 37.41 | Not recorded | 68fa6cb31e209131cea3554d |
| Global relight | 36.84 | Not recorded | 68fa6cb31e209131cea3554d |
| Day dimmed | 36.13 | Not recorded | 68fa6cb31e209131cea3554d |
| Day | 36.1 | Not recorded | 68fa6cb31e209131cea3554d |
| CycleGAN | 35.26 | Not recorded | 68fa6cb31e209131cea3554d |

### Supervised

PSNR: 39.74. Result ID: 698f2f503a6c314849f6cc9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

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

Recorded evaluation configuration: {"Training data composition":"Purely real"}. This record does not assert independent reproduction.

### Ours (90% Synthetic + 10% Real)

PSNR: 39.04. Result ID: 698f2f503a6c314849f6cc9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

[Implementation](<https://github.com/SamsungLabs/day-to-night>)

Recorded evaluation configuration: {"Training data composition":"Mix of synthetic and real"}. This record does not assert independent reproduction.

### Ours (95% Synthetic + 5% Real)

PSNR: 38.32. Result ID: 698f2f503a6c314849f6cc99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

[Implementation](<https://github.com/SamsungLabs/day-to-night>)

Recorded evaluation configuration: {"Training data composition":"Mix of synthetic and real"}. This record does not assert independent reproduction.

### Ours

PSNR: 37.41. Result ID: 698f2f503a6c314849f6cc98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

[Implementation](<https://github.com/SamsungLabs/day-to-night>)

Recorded evaluation configuration: {"Training data composition":"Synthetic only (day-to-night synthesis)"}. This record does not assert independent reproduction.

### Global relight

PSNR: 36.84. Result ID: 698f2f503a6c314849f6cc96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

Recorded evaluation configuration: {"Training data composition":"Synthetic only"}. This record does not assert independent reproduction.

### Day dimmed

PSNR: 36.13. Result ID: 698f2f503a6c314849f6cc95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

Recorded evaluation configuration: {"Training data composition":"Synthetic only"}. This record does not assert independent reproduction.

### Day

PSNR: 36.1. Result ID: 698f2f503a6c314849f6cc94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

Recorded evaluation configuration: {"Training data composition":"Synthetic only"}. This record does not assert independent reproduction.

### CycleGAN

PSNR: 35.26. Result ID: 698f2f503a6c314849f6cc97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3554d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68351e209131cea1ac7a.md>)

Recorded evaluation configuration: {"Training data composition":"Synthetic only"}. This record does not assert independent reproduction.

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