# Nonlinear Blur Deblurring on FFHQ 100 images (val)

Source: [Nonlinear Blur Deblurring on FFHQ 100 images (val)](<https://www.sota2.com/research/sota/nonlinear-blur-deblurring-on-ffhq-100-images-val>)

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

Data updated: 2026-03-19T08:59:58.823Z

Evaluation of Nonlinear Blur Deblurring performance using the validation subset consisting of 100 specific images from the FFHQ dataset, measured using SSIM, LPIPS, and FID.

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 | Nonlinear Blur Deblurring |
| Dataset (including any stated split) | FFHQ 100 images (val) |
| Metric | SSIM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [SSIM](<https://www.sota2.com/research/sota/nonlinear-blur-deblurring-on-ffhq-100-images-val.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/nonlinear-blur-deblurring-on-ffhq-100-images-val.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/nonlinear-blur-deblurring-on-ffhq-100-images-val.md?metric=FID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | SSIM | Result date | Report paper |
| --- | --- | --- | --- |
| DCDP | 80.3 | Not recorded | 6923e657d6b0dd334292ecfc |
| DAPS-1K | 76.2 | Not recorded | 6923e657d6b0dd334292ecfc |
| DAPS++-50 | 74.5 | Not recorded | 6923e657d6b0dd334292ecfc |
| DAPS-100 | 68.5 | Not recorded | 6923e657d6b0dd334292ecfc |
| DPS | 64.8 | Not recorded | 6923e657d6b0dd334292ecfc |

### DCDP

SSIM: 80.3. Result ID: 69bbbb0c47f34ce924a5bcc6.

[Reporting paper](<https://www.sota2.com/research/paper/6923e657d6b0dd334292ecfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792f1e209131cea7c791.md>)

Recorded evaluation configuration: {"Additive Gaussian noise level (gamma)":"0.05"}. This record does not assert independent reproduction.

### DAPS-1K

SSIM: 76.2. Result ID: 69bbbb0c47f34ce924a5bcc9.

[Reporting paper](<https://www.sota2.com/research/paper/6923e657d6b0dd334292ecfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa31e209131cea84481.md>)

Recorded evaluation configuration: {"Number of sampling steps (NFEs)":"1000","Additive Gaussian noise level (gamma)":"0.05"}. This record does not assert independent reproduction.

### DAPS++-50

SSIM: 74.5. Result ID: 69bbbb0c47f34ce924a5bcca.

[Reporting paper](<https://www.sota2.com/research/paper/6923e657d6b0dd334292ecfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6923e657d6b0dd334292ecfc.md>)

Recorded evaluation configuration: {"Number of sampling steps (NFEs)":"50","Additive Gaussian noise level (gamma)":"0.05"}. This record does not assert independent reproduction.

### DAPS-100

SSIM: 68.5. Result ID: 69bbbb0c47f34ce924a5bcc8.

[Reporting paper](<https://www.sota2.com/research/paper/6923e657d6b0dd334292ecfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa31e209131cea84481.md>)

Recorded evaluation configuration: {"Number of sampling steps (NFEs)":"100","Additive Gaussian noise level (gamma)":"0.05"}. This record does not assert independent reproduction.

### DPS

SSIM: 64.8. Result ID: 69bbbb0c47f34ce924a5bcc7.

[Reporting paper](<https://www.sota2.com/research/paper/6923e657d6b0dd334292ecfc.md>)

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

Recorded evaluation configuration: {"Additive Gaussian noise level (gamma)":"0.05"}. This record does not assert independent reproduction.

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