# Input Image Reconstruction on Deepfake Reconstruction Dataset

Source: [Input Image Reconstruction on Deepfake Reconstruction Dataset](<https://www.sota2.com/research/sota/input-image-reconstruction-on-deepfake-reconstruction-dataset>)

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

Data updated: 2026-02-26T05:50:37.339Z

Evaluation of image reconstruction models using the Deepfake Reconstruction Dataset, typically measured using perceptual and error metrics like MSE, SSIM, and PSNR.

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 | Input Image Reconstruction |
| Dataset (including any stated split) | Deepfake Reconstruction Dataset |
| Metric | MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

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

- [SSIM](<https://www.sota2.com/research/sota/input-image-reconstruction-on-deepfake-reconstruction-dataset.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [PSNR](<https://www.sota2.com/research/sota/input-image-reconstruction-on-deepfake-reconstruction-dataset.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [Feature Similarity](<https://www.sota2.com/research/sota/input-image-reconstruction-on-deepfake-reconstruction-dataset.md?metric=Feature%20Similarity>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MSE | Result date | Report paper |
| --- | --- | --- | --- |
| MagDR | 11.4 | Not recorded | 68fa699d1e209131cea23173 |
| Mustafa | 15.53 | Not recorded | 68fa699d1e209131cea23173 |
| Gintare | 17.69 | Not recorded | 68fa699d1e209131cea23173 |
| Yang | 21.17 | Not recorded | 68fa699d1e209131cea23173 |
| Nataniel | 24.59 | Not recorded | 68fa699d1e209131cea23173 |
| Prakash | 25.56 | Not recorded | 68fa699d1e209131cea23173 |
| Xie | 25.59 | Not recorded | 68fa699d1e209131cea23173 |
| Meng | 27.66 | Not recorded | 68fa699d1e209131cea23173 |

### MagDR

MSE: 11.4. Result ID: 698dc6ed8b517eb43323a84d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Implementation](<https://github.com/natanielruiz/disrupting-deepfakes>)

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

### Mustafa

MSE: 15.53. Result ID: 698dc6ed8b517eb43323a84c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e91e209131cea131e5.md>)

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

### Gintare

MSE: 17.69. Result ID: 698dc6ed8b517eb43323a84b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a51e209131ce9fa8d2.md>)

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

### Yang

MSE: 21.17. Result ID: 698dc6ed8b517eb43323a849.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65d91e209131cea0cc53.md>)

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

### Nataniel

MSE: 24.59. Result ID: 698dc6ed8b517eb43323a84a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676d1e209131cea16181.md>)

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

### Prakash

MSE: 25.56. Result ID: 698dc6ed8b517eb43323a847.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64301e209131cea03593.md>)

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

### Xie

MSE: 25.59. Result ID: 698dc6ed8b517eb43323a846.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640f1e209131cea026a7.md>)

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

### Meng

MSE: 27.66. Result ID: 698dc6ed8b517eb43323a848.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699d1e209131cea23173.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63a41e209131ce9fffb3.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.