# Image-to-Video on Koala-36M and RealEstate10K

Source: [Image-to-Video on Koala-36M and RealEstate10K](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k>)

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

Data updated: 2026-06-23T07:34:09.367Z

Evaluation of Image-to-Video generation models using a combined dataset featuring Koala-36M and RealEstate10K, assessed using metrics including FVD, FID, and CLIP Score.

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-to-Video |
| Dataset (including any stated split) | Koala-36M and RealEstate10K |
| Metric | FVD |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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

- [FVD](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=FVD>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=FID>): Lower is better; unit: SCALAR.

- [CLIP Score](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=CLIP%20Score>): Higher is better; unit: SCALAR.

- [VBench Visual Quality](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=VBench%20Visual%20Quality>): Higher is better; unit: SCALAR.

- [CLIP-F](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=CLIP-F>): Higher is better; unit: SCALAR.

- [VBench Dynamic Quality](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=VBench%20Dynamic%20Quality>): Higher is better; unit: SCALAR.

- [Erot](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=Erot>): Lower is better; unit: SCALAR.

- [Etrans](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=Etrans>): Higher is better; unit: SCALAR.

- [CamMC](<https://www.sota2.com/research/sota/image-to-video-on-koala-36m-and-realestate10k.md?metric=CamMC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FVD | Result date | Report paper |
| --- | --- | --- | --- |
| CamCloneMaster | 312.13 | Not recorded | 6a3a130c206542251d7c6f63 |
| TriMotion | 317.85 | Not recorded | 6a3a130c206542251d7c6f63 |
| TriMotion | 337.09 | Not recorded | 6a3a130c206542251d7c6f63 |
| TriMotion | 348.63 | Not recorded | 6a3a130c206542251d7c6f63 |
| CamI2V | 361.95 | Not recorded | 6a3a130c206542251d7c6f63 |
| MotionClone | 601.77 | Not recorded | 6a3a130c206542251d7c6f63 |

### CamCloneMaster

FVD: 312.13. Result ID: 6a3a36b1fbc373592c341644.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa791f1e209131cea7c3a8.md>)

Recorded evaluation configuration: {"Target Modality":"Video"}. This record does not assert independent reproduction.

### TriMotion

FVD: 317.85. Result ID: 6a3a36b1fbc373592c341647.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

Recorded evaluation configuration: {"Target Modality":"Pose"}. This record does not assert independent reproduction.

### TriMotion

FVD: 337.09. Result ID: 6a3a36b1fbc373592c341646.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

Recorded evaluation configuration: {"Target Modality":"Video"}. This record does not assert independent reproduction.

### TriMotion

FVD: 348.63. Result ID: 6a3a36b1fbc373592c341645.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

Recorded evaluation configuration: {"Target Modality":"Text"}. This record does not assert independent reproduction.

### CamI2V

FVD: 361.95. Result ID: 6a3a36b1fbc373592c341642.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75fd1e209131cea6ac5e.md>)

Recorded evaluation configuration: {"Target Modality":"Pose"}. This record does not assert independent reproduction.

### MotionClone

FVD: 601.77. Result ID: 6a3a36b1fbc373592c341643.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a130c206542251d7c6f63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754d1e209131cea66f56.md>)

Recorded evaluation configuration: {"Target Modality":"Video"}. This record does not assert independent reproduction.

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