# Image Editing on CelebA-HQ (test)

Source: [Image Editing on CelebA-HQ (test)](<https://www.sota2.com/research/sota/image-editing-on-celeba-hq-test>)

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

Data updated: 2026-02-26T06:03:28.849Z

Evaluation of general image editing performance on the test split of the CelebA-HQ dataset, typically measured using reconstruction quality metrics (SSIM, PSNR) and identity preservation 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 | Image Editing |
| Dataset (including any stated split) | CelebA-HQ (test) |
| Metric | SSIM |
| Unit | SCALAR |
| 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/image-editing-on-celeba-hq-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/image-editing-on-celeba-hq-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [ID-Sim](<https://www.sota2.com/research/sota/image-editing-on-celeba-hq-test.md?metric=ID-Sim>): Higher is better; unit: SCALAR.

- [Dir-CLIP](<https://www.sota2.com/research/sota/image-editing-on-celeba-hq-test.md?metric=Dir-CLIP>): Higher is better; unit: SCALAR.

## Recorded results

| Method | SSIM | Result date | Report paper |
| --- | --- | --- | --- |
| Self-attention Decomposition | 0.92 | Not recorded | 69004dec3ef7ccd74e5e29d4 |
| Pullback | 0.9 | Not recorded | 69004dec3ef7ccd74e5e29d4 |
| Asyrp | 0.88 | Not recorded | 69004dec3ef7ccd74e5e29d4 |
| LocoEdit | 0.87 | Not recorded | 69004dec3ef7ccd74e5e29d4 |
| NoiseCLR | 0.85 | Not recorded | 69004dec3ef7ccd74e5e29d4 |

### Self-attention Decomposition

SSIM: 0.92. Result ID: 699a441b5698665ec4cb33a1.

[Reporting paper](<https://www.sota2.com/research/paper/69004dec3ef7ccd74e5e29d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004dec3ef7ccd74e5e29d4.md>)

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

### Pullback

SSIM: 0.9. Result ID: 699a441b5698665ec4cb339e.

[Reporting paper](<https://www.sota2.com/research/paper/69004dec3ef7ccd74e5e29d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ecf0.md>)

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

### Asyrp

SSIM: 0.88. Result ID: 699a441b5698665ec4cb339d.

[Reporting paper](<https://www.sota2.com/research/paper/69004dec3ef7ccd74e5e29d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee11e209131cea429c6.md>)

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

### LocoEdit

SSIM: 0.87. Result ID: 699a441b5698665ec4cb339f.

[Reporting paper](<https://www.sota2.com/research/paper/69004dec3ef7ccd74e5e29d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74cf1e209131cea64030.md>)

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

### NoiseCLR

SSIM: 0.85. Result ID: 699a441b5698665ec4cb33a0.

[Reporting paper](<https://www.sota2.com/research/paper/69004dec3ef7ccd74e5e29d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71611e209131cea50fe5.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.