# 2D Dense Correspondence on Synthetic Dataset (test)

Source: [2D Dense Correspondence on Synthetic Dataset (test)](<https://www.sota2.com/research/sota/2d-dense-correspondence-on-synthetic-dataset-test>)

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

Data updated: 2026-02-26T05:34:03.378Z

Evaluation of 2D Dense Correspondence performance on the test split of the Synthetic Dataset, measured using pixel accuracy thresholds (e.g., 5px, 10px, 20px).

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 | 2D Dense Correspondence |
| Dataset (including any stated split) | Synthetic Dataset (test) |
| Metric | Accuracy (5px) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Accuracy (5px)](<https://www.sota2.com/research/sota/2d-dense-correspondence-on-synthetic-dataset-test.md?metric=Accuracy%20(5px)>): Higher is better; unit: PERCENT.

- [Accuracy (10px)](<https://www.sota2.com/research/sota/2d-dense-correspondence-on-synthetic-dataset-test.md?metric=Accuracy%20(10px)>): Higher is better; unit: PERCENT.

- [Accuracy (20px)](<https://www.sota2.com/research/sota/2d-dense-correspondence-on-synthetic-dataset-test.md?metric=Accuracy%20(20px)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (5px) | Result date | Report paper |
| --- | --- | --- | --- |
| BodyMap | 71.12 | Not recorded | 68fa6c9d1e209131cea34edc |
| BodyMap | 66.15 | Not recorded | 68fa6c9d1e209131cea34edc |
| CSE | 44.52 | Not recorded | 68fa6c9d1e209131cea34edc |
| DensePose | 25.93 | Not recorded | 68fa6c9d1e209131cea34edc |

### BodyMap

Accuracy (5px): 71.12. Result ID: 698f26803a6c314849f63adb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34edc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34edc.md>)

[Implementation](<https://nsarafianos.github.io/bodymap>)

Recorded evaluation configuration: {"Input":"RGB + CSE"}. This record does not assert independent reproduction.

### BodyMap

Accuracy (5px): 66.15. Result ID: 698f26803a6c314849f63ada.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34edc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34edc.md>)

[Implementation](<https://nsarafianos.github.io/bodymap>)

Recorded evaluation configuration: {"Input":"RGB-only"}. This record does not assert independent reproduction.

### CSE

Accuracy (5px): 44.52. Result ID: 698f26803a6c314849f63ad9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34edc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d71e209131cea1e8de.md>)

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

### DensePose

Accuracy (5px): 25.93. Result ID: 698f26803a6c314849f63ad8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34edc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640a1e209131cea023cf.md>)

[Implementation](<http://densepose.org/>)

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

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