# Gaussian Deblur on ImageNet256

Source: [Gaussian Deblur on ImageNet256](<https://www.sota2.com/research/sota/gaussian-deblur-on-imagenet256>)

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

Data updated: 2026-05-01T07:05:12.569Z

Evaluation of image deblurring performance using a Gaussian degradation model on the ImageNet 256x256 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 | Gaussian Deblur |
| Dataset (including any stated split) | ImageNet256 |
| Metric | LPIPS |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [LPIPS](<https://www.sota2.com/research/sota/gaussian-deblur-on-imagenet256.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/gaussian-deblur-on-imagenet256.md?metric=PSNR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | LPIPS | Result date | Report paper |
| --- | --- | --- | --- |
| ReSample | 0.44 | Not recorded | 68fa75e01e209131cea6a64d |
| VIPaint | 0.45 | Not recorded | 68fa75e01e209131cea6a64d |
| PSLD | 0.58 | Not recorded | 68fa75e01e209131cea6a64d |
| DPS | 0.6 | Not recorded | 68fa75e01e209131cea6a64d |

### ReSample

LPIPS: 0.44. Result ID: 69f450a047f34ce924d9bc42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e01e209131cea6a64d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea596ef.md>)

Recorded evaluation configuration: {"Priors":"LDM"}. This record does not assert independent reproduction.

### VIPaint

LPIPS: 0.45. Result ID: 69f450a047f34ce924d9bc41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e01e209131cea6a64d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e01e209131cea6a64d.md>)

Recorded evaluation configuration: {"Priors":"LDM"}. This record does not assert independent reproduction.

### PSLD

LPIPS: 0.58. Result ID: 69f450a047f34ce924d9bc43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e01e209131cea6a64d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe71e209131cea48057.md>)

[Implementation](<https://github.com/LituRout/PSLD>)

Recorded evaluation configuration: {"Priors":"LDM"}. This record does not assert independent reproduction.

### DPS

LPIPS: 0.6. Result ID: 69f450a047f34ce924d9bc44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e01e209131cea6a64d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bdd1e209131cea8adbc.md>)

Recorded evaluation configuration: {"Priors":"LDM"}. This record does not assert independent reproduction.

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