# Image Reconstruction on FFHQ X dataset high-quality (test)

Source: [Image Reconstruction on FFHQ X dataset high-quality (test)](<https://www.sota2.com/research/sota/image-reconstruction-on-ffhq-x-dataset-high-quality-test>)

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

Data updated: 2026-02-26T05:48:17.733Z

Evaluation of image reconstruction models on the test split of the high-quality variant of the FFHQ X dataset, utilizing metrics like LPIPS, MSE, MS-SSIM, ID-Sim, and FID-X.

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 | Image Reconstruction |
| Dataset (including any stated split) | FFHQ X dataset high-quality (test) |
| Metric | LPIPS |
| Unit | SCALAR |
| Direction | Lower 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

- [LPIPS](<https://www.sota2.com/research/sota/image-reconstruction-on-ffhq-x-dataset-high-quality-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [MSE](<https://www.sota2.com/research/sota/image-reconstruction-on-ffhq-x-dataset-high-quality-test.md?metric=MSE>): Lower is better; unit: SCALAR.

- [MS-SSIM](<https://www.sota2.com/research/sota/image-reconstruction-on-ffhq-x-dataset-high-quality-test.md?metric=MS-SSIM>): Higher is better; unit: SCALAR.

- [ID-Sim](<https://www.sota2.com/research/sota/image-reconstruction-on-ffhq-x-dataset-high-quality-test.md?metric=ID-Sim>): Higher is better; unit: SCALAR.

- [FID-X](<https://www.sota2.com/research/sota/image-reconstruction-on-ffhq-x-dataset-high-quality-test.md?metric=FID-X>): Lower is better; unit: SCALAR.

## Recorded results

| Method | LPIPS | Result date | Report paper |
| --- | --- | --- | --- |
| pSp-cs-Ref | 0.019 | Not recorded | 6940e7ce456146936284faed |
| H-space-cs | 0.179 | Not recorded | 6940e7ce456146936284faed |
| DiffAE-cs | 0.188 | Not recorded | 6940e7ce456146936284faed |
| pSp-cs | 0.19 | Not recorded | 6940e7ce456146936284faed |
| Double InfoGAN | 0.369 | Not recorded | 6940e7ce456146936284faed |
| Sep-VAE | 0.556 | Not recorded | 6940e7ce456146936284faed |
| MMc-VAE | 0.6 | Not recorded | 6940e7ce456146936284faed |

### pSp-cs-Ref

LPIPS: 0.019. Result ID: 69984d065698665ec4aa685f.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

Recorded evaluation configuration: {"Framework":"CS-StyleGAN","Refinement":"F-space"}. This record does not assert independent reproduction.

### H-space-cs

LPIPS: 0.179. Result ID: 69984d065698665ec4aa685d.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

Recorded evaluation configuration: {"Framework":"Common-Salient"}. This record does not assert independent reproduction.

### DiffAE-cs

LPIPS: 0.188. Result ID: 69984d065698665ec4aa685c.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

Recorded evaluation configuration: {"Framework":"CS-Diffusion"}. This record does not assert independent reproduction.

### pSp-cs

LPIPS: 0.19. Result ID: 69984d065698665ec4aa685e.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

Recorded evaluation configuration: {"Framework":"CS-StyleGAN"}. This record does not assert independent reproduction.

### Double InfoGAN

LPIPS: 0.369. Result ID: 69984d065698665ec4aa685b.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fe1e209131cea53f84.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Sep-VAE

LPIPS: 0.556. Result ID: 69984d065698665ec4aa685a.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d61e209131cea58d4d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MMc-VAE

LPIPS: 0.6. Result ID: 69984d065698665ec4aa6859.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd71e209131cea307d2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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