# Video Inpainting on VACE-Benchmark Higher-resolution 25 x 720P

Source: [Video Inpainting on VACE-Benchmark Higher-resolution 25 x 720P](<https://www.sota2.com/research/sota/video-inpainting-on-vace-benchmark-higher-resolution-25-x-720p>)

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

Data updated: 2026-03-26T14:41:44.971Z

Evaluation of video inpainting performance using the high-resolution 720P variant of the VACE-Benchmark, assessed using PSNR, SSIM, VFID, and VB metrics.

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 Inpainting |
| Dataset (including any stated split) | VACE-Benchmark Higher-resolution 25 x 720P |
| Metric | PSNR |
| 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

- [PSNR](<https://www.sota2.com/research/sota/video-inpainting-on-vace-benchmark-higher-resolution-25-x-720p.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/video-inpainting-on-vace-benchmark-higher-resolution-25-x-720p.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [VFID](<https://www.sota2.com/research/sota/video-inpainting-on-vace-benchmark-higher-resolution-25-x-720p.md?metric=VFID>): Lower is better; unit: SCALAR.

- [VB](<https://www.sota2.com/research/sota/video-inpainting-on-vace-benchmark-higher-resolution-25-x-720p.md?metric=VB>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| HetCache | 13.03 | Not recorded | 69c4bdbd0636e5bf4afc77e8 |
| TeaCache | 13.01 | Not recorded | 69c4bdbd0636e5bf4afc77e8 |
| Wan-VACE-1.3B | 12.61 | Not recorded | 69c4bdbd0636e5bf4afc77e8 |

### HetCache

PSNR: 13.03. Result ID: 69c545a647f34ce924af40da.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdbd0636e5bf4afc77e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bdbd0636e5bf4afc77e8.md>)

Recorded evaluation configuration: {"Backbone":"Wan-VACE-1.3B","Sampling Steps":"50","FLOPs":"107.89","Latency":"227.54","Speed":"2.91×"}. This record does not assert independent reproduction.

### TeaCache

PSNR: 13.01. Result ID: 69c545a647f34ce924af40d9.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdbd0636e5bf4afc77e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73524.md>)

Recorded evaluation configuration: {"Backbone":"Wan-VACE-1.3B","Sampling Steps":"50","FLOPs":"126.48","Latency":"276.05","Speed":"2.40×"}. This record does not assert independent reproduction.

### Wan-VACE-1.3B

PSNR: 12.61. Result ID: 69c545a647f34ce924af40d8.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdbd0636e5bf4afc77e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76f7d.md>)

Recorded evaluation configuration: {"Backbone":"Wan-VACE-1.3B","Sampling Steps":"100","FLOPs":"252.97","Latency":"662.49","Speed":"1.00×"}. This record does not assert independent reproduction.

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