# 3D Human Pose Reconstruction on PoseKernel 1.0 (minor participants)

Source: [3D Human Pose Reconstruction on PoseKernel 1.0 (minor participants)](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants>)

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

Data updated: 2026-02-26T05:46:25.541Z

Evaluation of 3D Human Pose Reconstruction performance on the PoseKernel 1.0 dataset, reporting error rates for specific anatomical joints (Head, Neck, Hand, etc.) and the overall mean error.

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 | 3D Human Pose Reconstruction |
| Dataset (including any stated split) | PoseKernel 1.0 (minor participants) |
| Metric | Head Error |
| Unit | SCALAR |
| Direction | Lower 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

- [Head Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Head%20Error>): Lower is better; unit: SCALAR.

- [Neck Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Neck%20Error>): Lower is better; unit: SCALAR.

- [Hand Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Hand%20Error>): Lower is better; unit: SCALAR.

- [Elbow Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Elbow%20Error>): Lower is better; unit: SCALAR.

- [Shoulder Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Shoulder%20Error>): Lower is better; unit: SCALAR.

- [Hip Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Hip%20Error>): Lower is better; unit: SCALAR.

- [Knee Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Knee%20Error>): Lower is better; unit: SCALAR.

- [Foot Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Foot%20Error>): Lower is better; unit: SCALAR.

- [Mean Error](<https://www.sota2.com/research/sota/3d-human-pose-reconstruction-on-posekernel-1-0-minor-participants.md?metric=Mean%20Error>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Head Error | Result date | Report paper |
| --- | --- | --- | --- |
| PoseKernelLifter | 8.56 | Not recorded | 68fa6b631e209131cea2df80 |
| Vis.+Audio x 2 | 10.13 | Not recorded | 68fa6b631e209131cea2df80 |
| Vis.: Frank | 42.07 | Not recorded | 68fa6b631e209131cea2df80 |
| Vis.:LfD | 57.49 | Not recorded | 68fa6b631e209131cea2df80 |
| Audio x 4 | 313.4 | Not recorded | 68fa6b631e209131cea2df80 |

### PoseKernelLifter

Head Error: 8.56. Result ID: 698e8636ffc3901de09e54ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

Recorded evaluation configuration: {"Modality":"Vision + Audio","Audio Channels":4}. This record does not assert independent reproduction.

### Vis.+Audio x 2

Head Error: 10.13. Result ID: 698e8636ffc3901de09e54eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

Recorded evaluation configuration: {"Modality":"Vision + Audio","Audio Channels":2}. This record does not assert independent reproduction.

### Vis.: Frank

Head Error: 42.07. Result ID: 698e8636ffc3901de09e54e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a981e209131cea29378.md>)

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

Recorded evaluation configuration: {"Modality":"Vision"}. This record does not assert independent reproduction.

### Vis.:LfD

Head Error: 57.49. Result ID: 698e8636ffc3901de09e54e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d01e209131cea00d8a.md>)

Recorded evaluation configuration: {"Modality":"Vision"}. This record does not assert independent reproduction.

### Audio x 4

Head Error: 313.4. Result ID: 698e8636ffc3901de09e54ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df80.md>)

Recorded evaluation configuration: {"Modality":"Audio","Audio Channels":4}. This record does not assert independent reproduction.

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