# Image Inpainting (95% masked) on ImageNet-64

Source: [Image Inpainting (95% masked) on ImageNet-64](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64>)

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

Data updated: 2026-06-16T11:16:25.907Z

Evaluation of image inpainting performance on the ImageNet-64 dataset using a 95% masking strategy, measured using PSNR, SSIM, LPIPS, FID, MMD, and CRPS metrics.

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 | Inpainting (95% masked) |
| Dataset (including any stated split) | ImageNet-64 |
| 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/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=FID>): Lower is better; unit: SCALAR.

- [MMD-pix](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=MMD-pix>): Lower is better; unit: SCALAR.

- [MMD-Inc](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=MMD-Inc>): Lower is better; unit: SCALAR.

- [CRPS-pix](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=CRPS-pix>): Lower is better; unit: SCALAR.

- [CRPS-Inc](<https://www.sota2.com/research/sota/image-inpainting-95-percent-masked-on-imagenet-64.md?metric=CRPS-Inc>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| EPS | 18.41 | Not recorded | 6a30d925d33dfb23e783d381 |
| EPS | 17.85 | Not recorded | 6a30d925d33dfb23e783d381 |
| ΠGDM | 16.09 | Not recorded | 6a30d925d33dfb23e783d381 |
| DDNM | 14.47 | Not recorded | 6a30d925d33dfb23e783d381 |
| DAPS | 14.2 | Not recorded | 6a30d925d33dfb23e783d381 |
| DPS | 14.14 | Not recorded | 6a30d925d33dfb23e783d381 |
| MPGD | 13.87 | Not recorded | 6a30d925d33dfb23e783d381 |

### EPS

PSNR: 18.41. Result ID: 6a31306ffbc373592c2e923e.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

Recorded evaluation configuration: {"NFE":"20"}. This record does not assert independent reproduction.

### EPS

PSNR: 17.85. Result ID: 6a31306ffbc373592c2e923d.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

Recorded evaluation configuration: {"NFE":"100"}. This record does not assert independent reproduction.

### ΠGDM

PSNR: 16.09. Result ID: 6a31306ffbc373592c2e923b.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

Recorded evaluation configuration: {"NFE":"100"}. This record does not assert independent reproduction.

### DDNM

PSNR: 14.47. Result ID: 6a31306ffbc373592c2e923a.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfb9.md>)

[Implementation](<https://github.com/wyhuai/DDNM>)

Recorded evaluation configuration: {"NFE":"100"}. This record does not assert independent reproduction.

### DAPS

PSNR: 14.2. Result ID: 6a31306ffbc373592c2e9239.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

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

Recorded evaluation configuration: {"NFE":"100"}. This record does not assert independent reproduction.

### DPS

PSNR: 14.14. Result ID: 6a31306ffbc373592c2e9238.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

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

Recorded evaluation configuration: {"NFE":"250"}. This record does not assert independent reproduction.

### MPGD

PSNR: 13.87. Result ID: 6a31306ffbc373592c2e923c.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d925d33dfb23e783d381.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea504ca.md>)

Recorded evaluation configuration: {"NFE":"100"}. This record does not assert independent reproduction.

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