# Video Reconstruction on High-motion video 160 videos (val)

Source: [Video Reconstruction on High-motion video 160 videos (val)](<https://www.sota2.com/research/sota/video-reconstruction-on-high-motion-video-160-videos-val>)

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

Data updated: 2026-04-15T10:22:56.310Z

Evaluation of video reconstruction models using the validation split of the 'High-motion video 160 videos' dataset, measured using metrics including rFVD, LPIPS, SSIM, and PSNR.

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 Reconstruction |
| Dataset (including any stated split) | High-motion video 160 videos (val) |
| Metric | rFVD |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 9 of 9 |
| 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

- [rFVD](<https://www.sota2.com/research/sota/video-reconstruction-on-high-motion-video-160-videos-val.md?metric=rFVD>): Lower is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/video-reconstruction-on-high-motion-video-160-videos-val.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/video-reconstruction-on-high-motion-video-160-videos-val.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [PSNR](<https://www.sota2.com/research/sota/video-reconstruction-on-high-motion-video-160-videos-val.md?metric=PSNR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | rFVD | Result date | Report paper |
| --- | --- | --- | --- |
| Wan 2.1 (patchify) | 19.5 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| Wan 2.2 (patchify) | 22.6 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| HBQ (M=4, tune lambda\_GAN) | 30.1 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| HBQ (w/o quant) | 43.2 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| HBQ (M=4) | 50.6 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| HBQ (w/o quant) | 144.6 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| HBQ (M=8) | 144.9 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| HBQ (M=6) | 148.8 | Not recorded | 69df1bcb7d0172140ec7bc27 |
| HBQ (M=4) | 163.6 | Not recorded | 69df1bcb7d0172140ec7bc27 |

### Wan 2.1 (patchify)

rFVD: 19.5. Result ID: 69df663647f34ce924c8be16.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

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

Recorded evaluation configuration: {"Tokenizer Type":"Continuous","Latent Channel":"64","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"16","Compress Ratio":"24"}. This record does not assert independent reproduction.

### Wan 2.2 (patchify)

rFVD: 22.6. Result ID: 69df663647f34ce924c8be17.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

Recorded evaluation configuration: {"Tokenizer Type":"Continuous","Latent Channel":"48","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"16","Compress Ratio":"27"}. This record does not assert independent reproduction.

### HBQ (M=4, tune lambda\_GAN)

rFVD: 30.1. Result ID: 69df663647f34ce924c8be1e.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Implementation](<https://github.com/MGenAI/GRN>)

Recorded evaluation configuration: {"Tokenizer Type":"Discrete","Latent Channel":"64","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"4","Compress Ratio":"96"}. This record does not assert independent reproduction.

### HBQ (w/o quant)

rFVD: 43.2. Result ID: 69df663647f34ce924c8be1c.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Implementation](<https://github.com/MGenAI/GRN>)

Recorded evaluation configuration: {"Tokenizer Type":"Continuous","Latent Channel":"64","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"16","Compress Ratio":"24"}. This record does not assert independent reproduction.

### HBQ (M=4)

rFVD: 50.6. Result ID: 69df663647f34ce924c8be1d.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Implementation](<https://github.com/MGenAI/GRN>)

Recorded evaluation configuration: {"Tokenizer Type":"Discrete","Latent Channel":"64","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"4","Compress Ratio":"96"}. This record does not assert independent reproduction.

### HBQ (w/o quant)

rFVD: 144.6. Result ID: 69df663647f34ce924c8be18.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Implementation](<https://github.com/MGenAI/GRN>)

Recorded evaluation configuration: {"Tokenizer Type":"Continuous","Latent Channel":"16","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"16","Compress Ratio":"96"}. This record does not assert independent reproduction.

### HBQ (M=8)

rFVD: 144.9. Result ID: 69df663647f34ce924c8be1b.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Implementation](<https://github.com/MGenAI/GRN>)

Recorded evaluation configuration: {"Tokenizer Type":"Discrete","Latent Channel":"16","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"8","Compress Ratio":"192"}. This record does not assert independent reproduction.

### HBQ (M=6)

rFVD: 148.8. Result ID: 69df663647f34ce924c8be1a.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Implementation](<https://github.com/MGenAI/GRN>)

Recorded evaluation configuration: {"Tokenizer Type":"Discrete","Latent Channel":"16","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"6","Compress Ratio":"256"}. This record does not assert independent reproduction.

### HBQ (M=4)

rFVD: 163.6. Result ID: 69df663647f34ce924c8be19.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc27.md>)

[Implementation](<https://github.com/MGenAI/GRN>)

Recorded evaluation configuration: {"Tokenizer Type":"Discrete","Latent Channel":"16","Spatial Stride":"16","Temporal Stride":"4","Channel Bits":"4","Compress Ratio":"384"}. This record does not assert independent reproduction.

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