# Group Dance Generation on AIOZ-GDance short-duration

Source: [Group Dance Generation on AIOZ-GDance short-duration](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration>)

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

Data updated: 2026-03-25T12:46:16.238Z

Evaluation of models generating short-duration group dance sequences using the AIOZ-GDance dataset, assessed using metrics including GMR, GMC, TIF, FID, Div, and PFC.

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 | Group Dance Generation |
| Dataset (including any stated split) | AIOZ-GDance short-duration |
| Metric | GMR |
| Unit | SCALAR |
| Direction | Higher 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

- [GMR](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration.md?metric=GMR>): Higher is better; unit: SCALAR.

- [GMC](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration.md?metric=GMC>): Higher is better; unit: SCALAR.

- [TIF](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration.md?metric=TIF>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration.md?metric=FID>): Lower is better; unit: SCALAR.

- [Div](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration.md?metric=Div>): Higher is better; unit: SCALAR.

- [PFC](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration.md?metric=PFC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | GMR | Result date | Report paper |
| --- | --- | --- | --- |
| EDGE | 70.26 | Not recorded | 69c36c190636e5bf4afc6517 |
| GCD | 30.22 | Not recorded | 69c36c190636e5bf4afc6517 |
| CoDancers | 26.34 | Not recorded | 69c36c190636e5bf4afc6517 |
| ST-GDance | 14.76 | Not recorded | 69c36c190636e5bf4afc6517 |
| TCDiff++ | 11.85 | Not recorded | 69c36c190636e5bf4afc6517 |
| ST-GDance++ | 10.85 | Not recorded | 69c36c190636e5bf4afc6517 |

### EDGE

GMR: 70.26. Result ID: 69c3d88947f34ce924ad1cab.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c190636e5bf4afc6517.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e0d1e209131cea3db38.md>)

Recorded evaluation configuration: {"FLOPs (G)":"12.50","Params (M)":"52.13","Train (min/epoch)":"0:24","Inf (s)":"8.6"}. This record does not assert independent reproduction.

### GCD

GMR: 30.22. Result ID: 69c3d88947f34ce924ad1cac.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c190636e5bf4afc6517.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710f1e209131cea4ef4e.md>)

[Implementation](<https://aioz-ai.github.io/GCD/>)

Recorded evaluation configuration: {"FLOPs (G)":"27.69","Params (M)":"62.16","Train (min/epoch)":"1:04","Inf (s)":"4.8"}. This record does not assert independent reproduction.

### CoDancers

GMR: 26.34. Result ID: 69c3d88947f34ce924ad1cad.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c190636e5bf4afc6517.md>)

Recorded evaluation configuration: {"FLOPs (G)":"53.95","Params (M)":"56.83","Train (min/epoch)":"0:56","Inf (s)":"4.5"}. This record does not assert independent reproduction.

### ST-GDance

GMR: 14.76. Result ID: 69c3d88947f34ce924ad1caf.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c190636e5bf4afc6517.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a451e209131cea82167.md>)

Recorded evaluation configuration: {"FLOPs (G)":"6.75","Params (M)":"50.21","Train (min/epoch)":"0:37","Inf (s)":"3.3"}. This record does not assert independent reproduction.

### TCDiff++

GMR: 11.85. Result ID: 69c3d88947f34ce924ad1cae.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c190636e5bf4afc6517.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be61e209131cea8b2a3.md>)

Recorded evaluation configuration: {"FLOPs (G)":"32.56","Params (M)":"70.42","Train (min/epoch)":"1:32","Inf (s)":"9.3"}. This record does not assert independent reproduction.

### ST-GDance++

GMR: 10.85. Result ID: 69c3d88947f34ce924ad1cb0.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c190636e5bf4afc6517.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c190636e5bf4afc6517.md>)

Recorded evaluation configuration: {"FLOPs (G)":"11.32","Params (M)":"51.64","Train (min/epoch)":"0:42","Inf (s)":"4.2"}. This record does not assert independent reproduction.

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