# 3D Object Detection on Waymo Open Dataset domain adaptation (test)

Source: [3D Object Detection on Waymo Open Dataset domain adaptation (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-domain-adaptation-test>)

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

Data updated: 2026-02-26T05:21:11.110Z

Evaluation of 3D Object Detection performance on the test split of the Waymo Open Dataset domain adaptation subset, typically reporting AP metrics across distance ranges.

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 Object Detection |
| Dataset (including any stated split) | Waymo Open Dataset domain adaptation (test) |
| Metric | 3D AP |
| Unit | PERCENT |
| Direction | Higher 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

- [3D AP](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-domain-adaptation-test.md?metric=3D%20AP>): Higher is better; unit: PERCENT.

- [AP (0-30m)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-domain-adaptation-test.md?metric=AP%20(0-30m)>): Higher is better; unit: PERCENT.

- [AP (30-50m)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-domain-adaptation-test.md?metric=AP%20(30-50m)>): Higher is better; unit: PERCENT.

- [AP (50+m)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-domain-adaptation-test.md?metric=AP%20(50%2Bm)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | 3D AP | Result date | Report paper |
| --- | --- | --- | --- |
| 3DAL | 78.04 | Not recorded | 68fa697c1e209131cea225c5 |
| HorizonLidar3D | 72.48 | Not recorded | 68fa697c1e209131cea225c5 |
| PV-RCNN-DA | 71.4 | Not recorded | 68fa697c1e209131cea225c5 |
| Multi-frame MVF++ | 70.01 | Not recorded | 68fa697c1e209131cea225c5 |
| CenterPoint | 67.04 | Not recorded | 68fa697c1e209131cea225c5 |
| PointPillar | 45.48 | Not recorded | 68fa697c1e209131cea225c5 |

### 3DAL

3D AP: 78.04. Result ID: 698dae438b517eb433231298.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

Recorded evaluation configuration: {"training\_set":"Waymo Open Dataset main train set"}. This record does not assert independent reproduction.

### HorizonLidar3D

3D AP: 72.48. Result ID: 698dae438b517eb433231297.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

Recorded evaluation configuration: {"source":"leaderboard \[2\]"}. This record does not assert independent reproduction.

### PV-RCNN-DA

3D AP: 71.4. Result ID: 698dae438b517eb433231295.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

Recorded evaluation configuration: {"source":"leaderboard \[2\]"}. This record does not assert independent reproduction.

### Multi-frame MVF++

3D AP: 70.01. Result ID: 698dae438b517eb433231294.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

Recorded evaluation configuration: {"training\_set":"Waymo Open Dataset main train set"}. This record does not assert independent reproduction.

### CenterPoint

3D AP: 67.04. Result ID: 698dae438b517eb433231296.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

Recorded evaluation configuration: {"source":"leaderboard \[2\]"}. This record does not assert independent reproduction.

### PointPillar

3D AP: 45.48. Result ID: 698dae438b517eb433231293.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea225c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c01e209131cea0c2bc.md>)

[Implementation](<https://github.com/nutonomy/second.pytorch>)

Recorded evaluation configuration: {"training\_set":"Waymo Open Dataset main train set"}. This record does not assert independent reproduction.

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