# Video Frame Interpolation on Internal Dataset (10-fold cross-validation)

Source: [Video Frame Interpolation on Internal Dataset (10-fold cross-validation)](<https://www.sota2.com/research/sota/video-frame-interpolation-on-internal-dataset-10-fold-cross-validation>)

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

Data updated: 2026-02-26T05:48:54.522Z

Evaluation of Video Frame Interpolation performance using an internal dataset configured for 10-fold cross-validation, measured using MAE, RMSE, PSNR, and SSIM.

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 | Video Frame Interpolation |
| Dataset (including any stated split) | Internal Dataset (10-fold cross-validation) |
| Metric | MAE |
| 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

- [MAE](<https://www.sota2.com/research/sota/video-frame-interpolation-on-internal-dataset-10-fold-cross-validation.md?metric=MAE>): Lower is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/video-frame-interpolation-on-internal-dataset-10-fold-cross-validation.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/video-frame-interpolation-on-internal-dataset-10-fold-cross-validation.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/video-frame-interpolation-on-internal-dataset-10-fold-cross-validation.md?metric=SSIM>): Higher is better; unit: SCALAR.

## Recorded results

| Method | MAE | Result date | Report paper |
| --- | --- | --- | --- |
| SepConv | 3.66 | Not recorded | 68fa638c1e209131ce9ff7c6 |
| MDP-Flow2 | 3.72 | Not recorded | 68fa638c1e209131ce9ff7c6 |
| DeepFlow2 | 3.89 | Not recorded | 68fa638c1e209131ce9ff7c6 |
| SepConv | 4.01 | Not recorded | 68fa638c1e209131ce9ff7c6 |
| AdaConv | 5.34 | Not recorded | 68fa638c1e209131ce9ff7c6 |
| Meyer et al. | 10.45 | Not recorded | 68fa638c1e209131ce9ff7c6 |

### SepConv

MAE: 3.66. Result ID: 698bfbfaf729bc7f68e739b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

[Implementation](<http://graphics.cs.pdx.edu/project/sepconv>)

Recorded evaluation configuration: {"loss":"L1","Resolution":"150x150","Number of samples":"250,000"}. This record does not assert independent reproduction.

### MDP-Flow2

MAE: 3.72. Result ID: 698bfbfaf729bc7f68e739b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

Recorded evaluation configuration: {"Resolution":"150x150","Number of samples":"250,000"}. This record does not assert independent reproduction.

### DeepFlow2

MAE: 3.89. Result ID: 698bfbfaf729bc7f68e739b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

Recorded evaluation configuration: {"Resolution":"150x150","Number of samples":"250,000"}. This record does not assert independent reproduction.

### SepConv

MAE: 4.01. Result ID: 698bfbfaf729bc7f68e739b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

[Implementation](<http://graphics.cs.pdx.edu/project/sepconv>)

Recorded evaluation configuration: {"loss":"LF","Resolution":"150x150","Number of samples":"250,000"}. This record does not assert independent reproduction.

### AdaConv

MAE: 5.34. Result ID: 698bfbfaf729bc7f68e739ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63321e209131ce9fd4f0.md>)

Recorded evaluation configuration: {"Resolution":"150x150","Number of samples":"250,000"}. This record does not assert independent reproduction.

### Meyer et al.

MAE: 10.45. Result ID: 698bfbfaf729bc7f68e739b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa638c1e209131ce9ff7c6.md>)

Recorded evaluation configuration: {"Resolution":"150x150","Number of samples":"250,000"}. This record does not assert independent reproduction.

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