# HOI Video Reenactment on AnchorCrafter HOI 81 frames

Source: [HOI Video Reenactment on AnchorCrafter HOI 81 frames](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames>)

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

Data updated: 2026-03-09T08:02:37.272Z

Evaluation of Hand-Object Interaction (HOI) Video Reenactment performance using metrics covering self-reenactment quality (PSNR, SSIM, LPIPS, FID, FVD), cross-reenactment quality, and user study results (VQ, RF) on the AnchorCrafter HOI 81 frames dataset.

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 | HOI Video Reenactment |
| Dataset (including any stated split) | AnchorCrafter HOI 81 frames |
| Metric | Self-Reenactment PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Self-Reenactment PSNR](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Self-Reenactment%20PSNR>): Higher is better; unit: SCALAR.

- [Self-Reenactment SSIM](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Self-Reenactment%20SSIM>): Higher is better; unit: PERCENT.

- [Self-Reenactment LPIPS](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Self-Reenactment%20LPIPS>): Lower is better; unit: SCALAR.

- [Self-Reenactment FID](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Self-Reenactment%20FID>): Lower is better; unit: SCALAR.

- [Self-Reenactment FVD](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Self-Reenactment%20FVD>): Lower is better; unit: SCALAR.

- [Self-Reenactment OC](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Self-Reenactment%20OC>): Higher is better; unit: PERCENT.

- [Cross-Reenactment FID](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Cross-Reenactment%20FID>): Lower is better; unit: SCALAR.

- [Cross-Reenactment FVD](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=Cross-Reenactment%20FVD>): Lower is better; unit: SCALAR.

- [User Study VQ](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=User%20Study%20VQ>): Higher is better; unit: SCALAR.

- [User Study RF](<https://www.sota2.com/research/sota/hoi-video-reenactment-on-anchorcrafter-hoi-81-frames.md?metric=User%20Study%20RF>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Self-Reenactment PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| GenHOI (Ours) | 31.71 | Not recorded | 69ae53de2d603e6de3e4288a |
| VACE | 28.6 | Not recorded | 69ae53de2d603e6de3e4288a |
| HOI-Swap | 24.29 | Not recorded | 69ae53de2d603e6de3e4288a |
| UniAnimate-DiT | 22.2 | Not recorded | 69ae53de2d603e6de3e4288a |
| MimicMotion | 20.13 | Not recorded | 69ae53de2d603e6de3e4288a |

### GenHOI (Ours)

Self-Reenactment PSNR: 31.71. Result ID: 69ae7e896dbb7075b9567421.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53de2d603e6de3e4288a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53de2d603e6de3e4288a.md>)

Recorded evaluation configuration: {"Setting":"Short video generation (81 frames)"}. This record does not assert independent reproduction.

### VACE

Self-Reenactment PSNR: 28.6. Result ID: 69ae7e896dbb7075b956741d.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53de2d603e6de3e4288a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77591e209131cea7298c.md>)

[Implementation](<https://ali-vilab.github.io/VACE-Page/>)

Recorded evaluation configuration: {"Setting":"Short video generation (81 frames)"}. This record does not assert independent reproduction.

### HOI-Swap

Self-Reenactment PSNR: 24.29. Result ID: 69ae7e896dbb7075b9567420.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53de2d603e6de3e4288a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75981e209131cea68d85.md>)

[Implementation](<https://vision.cs.utexas.edu/projects/HOI-Swap>)

Recorded evaluation configuration: {"Setting":"Short video generation (81 frames)"}. This record does not assert independent reproduction.

### UniAnimate-DiT

Self-Reenactment PSNR: 22.2. Result ID: 69ae7e896dbb7075b956741e.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53de2d603e6de3e4288a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78001e209131cea764ef.md>)

Recorded evaluation configuration: {"Setting":"Short video generation (81 frames)"}. This record does not assert independent reproduction.

### MimicMotion

Self-Reenactment PSNR: 20.13. Result ID: 69ae7e896dbb7075b956741f.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53de2d603e6de3e4288a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a61e209131cea7ea8c.md>)

Recorded evaluation configuration: {"Setting":"Short video generation (81 frames)"}. This record does not assert independent reproduction.

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