# Video Frame Interpolation on 4K1000FPS (8x)

Source: [Video Frame Interpolation on 4K1000FPS (8x)](<https://www.sota2.com/research/sota/video-frame-interpolation-on-4k1000fps-8x>)

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

Data updated: 2026-02-26T05:55:39.907Z

Evaluation of Video Frame Interpolation performance on the 4K1000FPS dataset using an 8x frame rate increase, measured using 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) | 4K1000FPS 8x interpolation |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [PSNR](<https://www.sota2.com/research/sota/video-frame-interpolation-on-4k1000fps-8x.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/video-frame-interpolation-on-4k1000fps-8x.md?metric=SSIM>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| ABME | 30.16 | Not recorded | 68fa6dd31e209131cea3c394 |
| XVFI | 30.12 | Not recorded | 68fa6dd31e209131cea3c394 |
| EBME-H\* | 29.46 | Not recorded | 68fa6dd31e209131cea3c394 |
| EBME-H | 28.72 | Not recorded | 68fa6dd31e209131cea3c394 |
| EBME | 27.86 | Not recorded | 68fa6dd31e209131cea3c394 |
| DAIN | 26.78 | Not recorded | 68fa6dd31e209131cea3c394 |
| AdaCoF | 23.9 | Not recorded | 68fa6dd31e209131cea3c394 |

### ABME

PSNR: 30.16. Result ID: 698fde793a6c314849fc6f54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a8b1e209131cea28aaf.md>)

[Implementation](<https://github.com/JunHeum/ABME>)

Recorded evaluation configuration: {"arbitrary-time":true,"reuse flow":false}. This record does not assert independent reproduction.

### XVFI

PSNR: 30.12. Result ID: 698fde793a6c314849fc6f55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a7d1e209131cea2895f.md>)

[Implementation](<https://github.com/JihyongOh/XVFI>)

Recorded evaluation configuration: {"arbitrary-time":true,"reuse flow":"partial"}. This record does not assert independent reproduction.

### EBME-H\*

PSNR: 29.46. Result ID: 698fde793a6c314849fc6f58.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Implementation](<https://github.com/srcn-ivl/EBME>)

Recorded evaluation configuration: {"arbitrary-time":true,"reuse flow":true}. This record does not assert independent reproduction.

### EBME-H

PSNR: 28.72. Result ID: 698fde793a6c314849fc6f57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Implementation](<https://github.com/srcn-ivl/EBME>)

Recorded evaluation configuration: {"arbitrary-time":true,"reuse flow":true}. This record does not assert independent reproduction.

### EBME

PSNR: 27.86. Result ID: 698fde793a6c314849fc6f56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Implementation](<https://github.com/srcn-ivl/EBME>)

Recorded evaluation configuration: {"arbitrary-time":true,"reuse flow":true}. This record does not assert independent reproduction.

### DAIN

PSNR: 26.78. Result ID: 698fde793a6c314849fc6f52.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa658e1e209131cea0b1fb.md>)

[Implementation](<https://github.com/baowenbo/DAIN>)

Recorded evaluation configuration: {"arbitrary-time":true,"reuse flow":true}. This record does not assert independent reproduction.

### AdaCoF

PSNR: 23.9. Result ID: 698fde793a6c314849fc6f53.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c394.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67381e209131cea14eef.md>)

[Implementation](<https://github.com/HyeongminLEE/AdaCoF-pytorch>)

Recorded evaluation configuration: {"arbitrary-time":false,"reuse flow":false}. This record does not assert independent reproduction.

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