# Scene flow estimation on proprietary dataset (test)

Source: [Scene flow estimation on proprietary dataset (test)](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test>)

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

Data updated: 2026-04-29T07:31:47.919Z

Evaluation of Scene flow estimation performance on the test split of the proprietary dataset, measured using metrics including MEPE, MagE, DirE, AccS, AccR, AvgEPE, and SEPE.

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 | Scene flow estimation |
| Dataset (including any stated split) | proprietary dataset (test) |
| Metric | MEPE |
| Unit | SCALAR |
| Direction | Lower 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

- [MEPE](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test.md?metric=MEPE>): Lower is better; unit: SCALAR.

- [MagE](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test.md?metric=MagE>): Lower is better; unit: SCALAR.

- [DirE](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test.md?metric=DirE>): Lower is better; unit: SCALAR.

- [AccS](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test.md?metric=AccS>): Higher is better; unit: PERCENT.

- [AccR](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test.md?metric=AccR>): Higher is better; unit: PERCENT.

- [AvgEPE](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test.md?metric=AvgEPE>): Lower is better; unit: SCALAR.

- [SEPE](<https://www.sota2.com/research/sota/scene-flow-estimation-on-proprietary-dataset-test.md?metric=SEPE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MEPE | Result date | Report paper |
| --- | --- | --- | --- |
| TARS | 0.069 | Not recorded | 68fa7a361e209131cea81d35 |
| HALFlow | 0.17 | Not recorded | 68fa7a361e209131cea81d35 |
| PointPWC-Net | 0.213 | Not recorded | 68fa7a361e209131cea81d35 |
| PointPWC-Net | 0.453 | Not recorded | 68fa7a361e209131cea81d35 |

### TARS

MEPE: 0.069. Result ID: 69f1b3a947f34ce924d7d74e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a361e209131cea81d35.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a361e209131cea81d35.md>)

Recorded evaluation configuration: {"PointGRU":"true","setup":"superego"}. This record does not assert independent reproduction.

### HALFlow

MEPE: 0.17. Result ID: 69f1b3a947f34ce924d7d74d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a361e209131cea81d35.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a231e209131cea264e4.md>)

Recorded evaluation configuration: {"PointGRU":"true","setup":"superego"}. This record does not assert independent reproduction.

### PointPWC-Net

MEPE: 0.213. Result ID: 69f1b3a947f34ce924d7d74c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a361e209131cea81d35.md>)

Recorded evaluation configuration: {"PointGRU":"true","setup":"superego"}. This record does not assert independent reproduction.

### PointPWC-Net

MEPE: 0.453. Result ID: 69f1b3a947f34ce924d7d74b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a361e209131cea81d35.md>)

Recorded evaluation configuration: {"PointGRU":"false","setup":"superego"}. This record does not assert independent reproduction.

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