# Random Inpainting on ImageNet 92% mask 256x256 (val)

Source: [Random Inpainting on ImageNet 92% mask 256x256 (val)](<https://www.sota2.com/research/sota/random-inpainting-on-imagenet-92-percent-mask-256x256-val>)

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

Data updated: 2026-04-21T09:15:49.606Z

Evaluation of image inpainting performance using a random masking strategy (92% coverage) on the validation split of ImageNet at 256x256 resolution, measured using PSNR, SSIM, and LPIPS.

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 | Random Inpainting |
| Dataset (including any stated split) | ImageNet 92% mask 256x256 (val) |
| 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/random-inpainting-on-imagenet-92-percent-mask-256x256-val.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/random-inpainting-on-imagenet-92-percent-mask-256x256-val.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/random-inpainting-on-imagenet-92-percent-mask-256x256-val.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| NA-NHMC | 24.1 | Not recorded | 69e704bb7d0172140ec7ee70 |
| SITCOM | 23.89 | Not recorded | 69e704bb7d0172140ec7ee70 |
| DMPlug | 23.49 | Not recorded | 69e704bb7d0172140ec7ee70 |
| DAPS | 23.23 | Not recorded | 69e704bb7d0172140ec7ee70 |
| DPS | 22.31 | Not recorded | 69e704bb7d0172140ec7ee70 |
| DiffPIR | 19.3 | Not recorded | 69e704bb7d0172140ec7ee70 |
| RED-diff | 17.25 | Not recorded | 69e704bb7d0172140ec7ee70 |

### NA-NHMC

PSNR: 24.1. Result ID: 69e7403b47f34ce924cdbb5a.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

Recorded evaluation configuration: {"Masking Ratio":"92%","Gaussian Noise Level (sigma\_y)":"0.05"}. This record does not assert independent reproduction.

### SITCOM

PSNR: 23.89. Result ID: 69e7403b47f34ce924cdbb58.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78db1e209131cea7ad48.md>)

Recorded evaluation configuration: {"Masking Ratio":"92%","Gaussian Noise Level (sigma\_y)":"0.05"}. This record does not assert independent reproduction.

### DMPlug

PSNR: 23.49. Result ID: 69e7403b47f34ce924cdbb59.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa758c1e209131cea688b2.md>)

Recorded evaluation configuration: {"Masking Ratio":"92%","Gaussian Noise Level (sigma\_y)":"0.05"}. This record does not assert independent reproduction.

### DAPS

PSNR: 23.23. Result ID: 69e7403b47f34ce924cdbb57.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

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

Recorded evaluation configuration: {"Masking Ratio":"92%","Gaussian Noise Level (sigma\_y)":"0.05"}. This record does not assert independent reproduction.

### DPS

PSNR: 22.31. Result ID: 69e7403b47f34ce924cdbb56.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

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

Recorded evaluation configuration: {"Masking Ratio":"92%","Gaussian Noise Level (sigma\_y)":"0.05"}. This record does not assert independent reproduction.

### DiffPIR

PSNR: 19.3. Result ID: 69e7403b47f34ce924cdbb54.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f5a1e209131cea45311.md>)

Recorded evaluation configuration: {"Masking Ratio":"92%","Gaussian Noise Level (sigma\_y)":"0.05"}. This record does not assert independent reproduction.

### RED-diff

PSNR: 17.25. Result ID: 69e7403b47f34ce924cdbb55.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee70.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5af61e209131ce9c4296.md>)

Recorded evaluation configuration: {"Masking Ratio":"92%","Gaussian Noise Level (sigma\_y)":"0.05"}. This record does not assert independent reproduction.

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