# Image Immunization on SVD pipeline

Source: [Image Immunization on SVD pipeline](<https://www.sota2.com/research/sota/image-immunization-on-svd-pipeline>)

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

Data updated: 2026-04-07T07:28:57.620Z

Evaluation of Image Immunization performance using the SVD pipeline, assessed using temporal consistency, flow magnitude, aesthetic quality, subject consistency, LPIPS, and human evaluation scores.

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 Immunization |
| Dataset (including any stated split) | SVD pipeline |
| Metric | Temporal SSIM |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Temporal SSIM](<https://www.sota2.com/research/sota/image-immunization-on-svd-pipeline.md?metric=Temporal%20SSIM>): Higher is better; unit: SCALAR.

- [Flow Magnitude](<https://www.sota2.com/research/sota/image-immunization-on-svd-pipeline.md?metric=Flow%20Magnitude>): Higher is better; unit: SCALAR.

- [Aesthetic Score](<https://www.sota2.com/research/sota/image-immunization-on-svd-pipeline.md?metric=Aesthetic%20Score>): Higher is better; unit: SCALAR.

- [Subject Consistency](<https://www.sota2.com/research/sota/image-immunization-on-svd-pipeline.md?metric=Subject%20Consistency>): Higher is better; unit: SCALAR.

- [LPIPS (X, X\_adv)](<https://www.sota2.com/research/sota/image-immunization-on-svd-pipeline.md?metric=LPIPS%20(X%2C%20X_adv)>): Lower is better; unit: SCALAR.

- [Human Evaluation Score](<https://www.sota2.com/research/sota/image-immunization-on-svd-pipeline.md?metric=Human%20Evaluation%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Temporal SSIM | Result date | Report paper |
| --- | --- | --- | --- |
| Original Image | 0.305 | Not recorded | 68fa7bb21e209131cea89f3d |
| I2VGuard\* | 0.186 | Not recorded | 68fa7bb21e209131cea89f3d |
| VidFreeze | 0.014 | Not recorded | 68fa7bb21e209131cea89f3d |

### Original Image

Temporal SSIM: 0.305. Result ID: 69d4b23847f34ce924bc2175.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb21e209131cea89f3d.md>)

Recorded evaluation configuration: {"Model":"SVD","epsilon":"16"}. This record does not assert independent reproduction.

### I2VGuard\*

Temporal SSIM: 0.186. Result ID: 69d4b23847f34ce924bc2176.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb21e209131cea89f3d.md>)

Recorded evaluation configuration: {"Model":"SVD","epsilon":"16"}. This record does not assert independent reproduction.

### VidFreeze

Temporal SSIM: 0.014. Result ID: 69d4b23847f34ce924bc2177.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb21e209131cea89f3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb21e209131cea89f3d.md>)

Recorded evaluation configuration: {"Model":"SVD","epsilon":"16"}. This record does not assert independent reproduction.

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