# Human Motion Prediction on 3DPW synthetic noise zero-shot (test)

Source: [Human Motion Prediction on 3DPW synthetic noise zero-shot (test)](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test>)

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

Data updated: 2026-02-26T05:21:40.615Z

Evaluation of models on predicting future human motion sequences using the zero-shot test split of the 3DPW dataset under synthetic noise conditions.

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 | Human Motion Prediction |
| Dataset (including any stated split) | 3DPW synthetic noise zero-shot (test) |
| Metric | ADE |
| Unit | SCALAR |
| Direction | Lower 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

- [ADE](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=ADE>): Lower is better; unit: SCALAR.

- [FDE](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=FDE>): Lower is better; unit: SCALAR.

- [MAE](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=MAE>): Lower is better; unit: SCALAR.

- [MMADE](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=MMADE>): Lower is better; unit: SCALAR.

- [MMFDE](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=MMFDE>): Lower is better; unit: SCALAR.

- [APD](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=APD>): Lower is better; unit: SCALAR.

- [CMD](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=CMD>): Lower is better; unit: SCALAR.

- [Body Realism Mean (str)](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=Body%20Realism%20Mean%20(str)>): Higher is better; unit: SCALAR.

- [Body Realism Mean (jit)](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=Body%20Realism%20Mean%20(jit)>): Higher is better; unit: SCALAR.

- [Body Realism RMSE (str)](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=Body%20Realism%20RMSE%20(str)>): Lower is better; unit: SCALAR.

- [Body Realism RMSE (jit)](<https://www.sota2.com/research/sota/human-motion-prediction-on-3dpw-synthetic-noise-zero-shot-test.md?metric=Body%20Realism%20RMSE%20(jit)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | ADE | Result date | Report paper |
| --- | --- | --- | --- |
| BeLFusion | 0.507 | Not recorded | 68fa79ef1e209131cea8018d |
| SkeletonDiffusion | 0.512 | Not recorded | 68fa79ef1e209131cea8018d |
| CoMusion | 0.55 | Not recorded | 68fa79ef1e209131cea8018d |
| DivSamp | 0.583 | Not recorded | 68fa79ef1e209131cea8018d |
| DLow | 0.596 | Not recorded | 68fa79ef1e209131cea8018d |
| ZeroVelocity | 0.764 | Not recorded | 68fa79ef1e209131cea8018d |

### BeLFusion

ADE: 0.507. Result ID: 698b66b17a967eddb76e45cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49dca.md>)

[Implementation](<https://barquerogerman.github.io/BeLFusion/>)

Recorded evaluation configuration: {"Type":"DM","Zero-shot":true}. This record does not assert independent reproduction.

### SkeletonDiffusion

ADE: 0.512. Result ID: 698b66b17a967eddb76e45cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018d.md>)

Recorded evaluation configuration: {"Type":"DM","Zero-shot":true}. This record does not assert independent reproduction.

### CoMusion

ADE: 0.55. Result ID: 698b66b17a967eddb76e45cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018d.md>)

Recorded evaluation configuration: {"Type":"DM","Zero-shot":true}. This record does not assert independent reproduction.

### DivSamp

ADE: 0.583. Result ID: 698b66b17a967eddb76e45ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfb1e209131cea3713f.md>)

Recorded evaluation configuration: {"Type":"VAE","Zero-shot":true}. This record does not assert independent reproduction.

### DLow

ADE: 0.596. Result ID: 698b66b17a967eddb76e45c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680b1e209131cea19c78.md>)

[Implementation](<https://www.ye-yuan.com/dlow>)

Recorded evaluation configuration: {"Type":"VAE","Zero-shot":true}. This record does not assert independent reproduction.

### ZeroVelocity

ADE: 0.764. Result ID: 698b66b17a967eddb76e45c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018d.md>)

Recorded evaluation configuration: {"Type":"Alg","Zero-shot":true}. This record does not assert independent reproduction.

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