# 3D Human Reconstruction on Synthetic Five Sequences f1, f2, f3, m1, m2

Source: [3D Human Reconstruction on Synthetic Five Sequences f1, f2, f3, m1, m2](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2>)

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

Data updated: 2026-02-26T05:42:11.912Z

Evaluation of 3D Human Reconstruction performance on the specific sequences (f1, f2, f3, m1, m2) derived from the Synthetic dataset, reporting metrics including Chamfer distance and sequence-specific error scores.

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 Reconstruction |
| Dataset (including any stated split) | Synthetic Five Sequences f1, f2, f3, m1, m2 |
| Metric | Error (f1 Sequence) |
| 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

- [Error (f1 Sequence)](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Error%20(f1%20Sequence)>): Lower is better; unit: SCALAR.

- [Recon Error](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Recon%20Error>): Lower is better; unit: SCALAR.

- [Ground Truth Reference](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Ground%20Truth%20Reference>): Higher is better; unit: SCALAR.

- [Chamfer Distance (CD)](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Chamfer%20Distance%20(CD)>): Lower is better; unit: SCALAR.

- [Error (f2 Sequence)](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Error%20(f2%20Sequence)>): Lower is better; unit: SCALAR.

- [Error (f3 Sequence)](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Error%20(f3%20Sequence)>): Lower is better; unit: SCALAR.

- [Error (m1 Sequence)](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Error%20(m1%20Sequence)>): Lower is better; unit: SCALAR.

- [Error (m2 Sequence)](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Error%20(m2%20Sequence)>): Lower is better; unit: SCALAR.

- [Mean Error](<https://www.sota2.com/research/sota/3d-human-reconstruction-on-synthetic-five-sequences-f1-f2-f3-m1-m2.md?metric=Mean%20Error>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Error (f1 Sequence) | Result date | Report paper |
| --- | --- | --- | --- |
| VideoAvatar | 1.59 | Not recorded | 68fa6c2a1e209131cea32790 |
| SelfRecon | 1.62 | Not recorded | 68fa6c2a1e209131cea32790 |
| SelfRecon | 1.64 | Not recorded | 68fa6c2a1e209131cea32790 |
| SelfRecon | 1.67 | Not recorded | 68fa6c2a1e209131cea32790 |
| VideoAvatar | 1.84 | Not recorded | 68fa6c2a1e209131cea32790 |
| VideoAvatar | 2.08 | Not recorded | 68fa6c2a1e209131cea32790 |

### VideoAvatar

Error (f1 Sequence): 1.59. Result ID: 698ee583a4474a45981fea7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64491e209131cea03b71.md>)

Recorded evaluation configuration: {"Metric Category":"Average distance from reconstructed to GT meshes (Recon)"}. This record does not assert independent reproduction.

### SelfRecon

Error (f1 Sequence): 1.62. Result ID: 698ee583a4474a45981fea80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Implementation](<https://github.com/jby1993/SelfReconCode>)

Recorded evaluation configuration: {"Metric Category":"Average distance from GT to reconstructed meshes (GT)"}. This record does not assert independent reproduction.

### SelfRecon

Error (f1 Sequence): 1.64. Result ID: 698ee583a4474a45981fea82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Implementation](<https://github.com/jby1993/SelfReconCode>)

Recorded evaluation configuration: {"Metric Category":"Chamfer distance (Chamfer)"}. This record does not assert independent reproduction.

### SelfRecon

Error (f1 Sequence): 1.67. Result ID: 698ee583a4474a45981fea7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Implementation](<https://github.com/jby1993/SelfReconCode>)

Recorded evaluation configuration: {"Metric Category":"Average distance from reconstructed to GT meshes (Recon)"}. This record does not assert independent reproduction.

### VideoAvatar

Error (f1 Sequence): 1.84. Result ID: 698ee583a4474a45981fea81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64491e209131cea03b71.md>)

Recorded evaluation configuration: {"Metric Category":"Chamfer distance (Chamfer)"}. This record does not assert independent reproduction.

### VideoAvatar

Error (f1 Sequence): 2.08. Result ID: 698ee583a4474a45981fea7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64491e209131cea03b71.md>)

Recorded evaluation configuration: {"Metric Category":"Average distance from GT to reconstructed meshes (GT)"}. This record does not assert independent reproduction.

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