# 3D Object Detection on RZDG Real

Source: [3D Object Detection on RZDG Real](<https://www.sota2.com/research/sota/3d-object-detection-on-rzdg-real>)

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

Data updated: 2026-07-07T10:18:34.782Z

Evaluation of 3D Object Detection performance on the RZDG Real dataset, reporting AP3D and APBEV metrics across Easy, Moderate, and Hard difficulty levels.

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) | RZDG Real |
| Metric | AP3D (Easy) |
| 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

- [AP3D (Easy)](<https://www.sota2.com/research/sota/3d-object-detection-on-rzdg-real.md?metric=AP3D%20(Easy)>): Higher is better; unit: PERCENT.

- [AP3D (Moderate)](<https://www.sota2.com/research/sota/3d-object-detection-on-rzdg-real.md?metric=AP3D%20(Moderate)>): Higher is better; unit: PERCENT.

- [AP3D (Hard)](<https://www.sota2.com/research/sota/3d-object-detection-on-rzdg-real.md?metric=AP3D%20(Hard)>): Higher is better; unit: PERCENT.

- [APBEV (Easy)](<https://www.sota2.com/research/sota/3d-object-detection-on-rzdg-real.md?metric=APBEV%20(Easy)>): Higher is better; unit: PERCENT.

- [APBEV (Moderate)](<https://www.sota2.com/research/sota/3d-object-detection-on-rzdg-real.md?metric=APBEV%20(Moderate)>): Higher is better; unit: PERCENT.

- [APBEV (Hard)](<https://www.sota2.com/research/sota/3d-object-detection-on-rzdg-real.md?metric=APBEV%20(Hard)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP3D (Easy) | Result date | Report paper |
| --- | --- | --- | --- |
| MVXNet | 39.272 | Not recorded | 6a4c882e85dba69fef8b2b5f |
| MVXNet | 32.825 | Not recorded | 6a4c882e85dba69fef8b2b5f |
| PointPillars | 32.4564 | Not recorded | 6a4c882e85dba69fef8b2b5f |
| PointPillars | 26.9185 | Not recorded | 6a4c882e85dba69fef8b2b5f |
| SMOKE | 1.656 | Not recorded | 6a4c882e85dba69fef8b2b5f |
| SMOKE | 0.283 | Not recorded | 6a4c882e85dba69fef8b2b5f |

### MVXNet

AP3D (Easy): 39.272. Result ID: 6a4cd26660b88bb339ca6b06.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa658f1e209131cea0b2fd.md>)

Recorded evaluation configuration: {"Modality":"C, L","Class":"Road beacon"}. This record does not assert independent reproduction.

### MVXNet

AP3D (Easy): 32.825. Result ID: 6a4cd26660b88bb339ca6b09.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa658f1e209131cea0b2fd.md>)

Recorded evaluation configuration: {"Modality":"C, L","Class":"Barrier"}. This record does not assert independent reproduction.

### PointPillars

AP3D (Easy): 32.4564. Result ID: 6a4cd26660b88bb339ca6b05.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b5f.md>)

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

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

Recorded evaluation configuration: {"Modality":"L","Class":"Road beacon"}. This record does not assert independent reproduction.

### PointPillars

AP3D (Easy): 26.9185. Result ID: 6a4cd26660b88bb339ca6b08.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b5f.md>)

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

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

Recorded evaluation configuration: {"Modality":"L","Class":"Barrier"}. This record does not assert independent reproduction.

### SMOKE

AP3D (Easy): 1.656. Result ID: 6a4cd26660b88bb339ca6b07.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67181e209131cea1418c.md>)

Recorded evaluation configuration: {"Modality":"C","Class":"Barrier"}. This record does not assert independent reproduction.

### SMOKE

AP3D (Easy): 0.283. Result ID: 6a4cd26660b88bb339ca6b04.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67181e209131cea1418c.md>)

Recorded evaluation configuration: {"Modality":"C","Class":"Road beacon"}. This record does not assert independent reproduction.

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