# Trajectory-controlled Motion Generation on HumanML3D 2022 (test)

Source: [Trajectory-controlled Motion Generation on HumanML3D 2022 (test)](<https://www.sota2.com/research/sota/trajectory-controlled-motion-generation-on-humanml3d-2022-test>)

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

Data updated: 2026-02-26T05:59:14.270Z

Evaluation of models generating human motion sequences conditioned on trajectory inputs, using the test split of the HumanML3D 2022 dataset, typically measured using R-precision, FID, and Diversity 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 | Trajectory-controlled motion generation |
| Dataset (including any stated split) | HumanML3D 2022 (test) |
| Metric | R-Precision |
| Unit | PERCENT |
| 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

- [R-Precision](<https://www.sota2.com/research/sota/trajectory-controlled-motion-generation-on-humanml3d-2022-test.md?metric=R-Precision>): Higher is better; unit: PERCENT.

- [FID](<https://www.sota2.com/research/sota/trajectory-controlled-motion-generation-on-humanml3d-2022-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [Diversity](<https://www.sota2.com/research/sota/trajectory-controlled-motion-generation-on-humanml3d-2022-test.md?metric=Diversity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | R-Precision | Result date | Report paper |
| --- | --- | --- | --- |
| Ground Truth | 80 | Not recorded | 68fa706f1e209131cea4af49 |
| Fine-tuned (Ours) | 64 | Not recorded | 68fa706f1e209131cea4af49 |
| MDM | 63 | Not recorded | 68fa706f1e209131cea4af49 |

### Ground Truth

R-Precision: 80. Result ID: 69912f533a6c314849064dcf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Fine-tuned (Ours)

R-Precision: 64. Result ID: 69912f533a6c314849064dd1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

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

Recorded evaluation configuration: {"Protocol":"Fine-tuned","Guidance scale":2.5}. This record does not assert independent reproduction.

### MDM

R-Precision: 63. Result ID: 69912f533a6c314849064dd0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8f1e209131cea3a994.md>)

[Implementation](<https://github.com/GuyTevet/motion-diffusion-model>)

Recorded evaluation configuration: {"Protocol":"Inpainting","Guidance scale":2.5}. This record does not assert independent reproduction.

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