# 3D Object Detection on RADIal refined 3D ground-truth (test)

Source: [3D Object Detection on RADIal refined 3D ground-truth (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-radial-refined-3d-ground-truth-test>)

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

Data updated: 2026-02-26T05:21:14.406Z

Evaluation of 3D Object Detection performance on the test split of the RADIal refined 3D ground-truth dataset, reporting metrics including 3D AP across distance ranges, ATE, ASE, and AOE.

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) | RADIal refined 3D ground-truth (test) |
| Metric | 3D AP@0.5 Overall |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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@0.5 Overall](<https://www.sota2.com/research/sota/3d-object-detection-on-radial-refined-3d-ground-truth-test.md?metric=3D%20AP%400.5%20Overall>): Higher is better; unit: PERCENT.

- [3D AP@0.5 (0-50m)](<https://www.sota2.com/research/sota/3d-object-detection-on-radial-refined-3d-ground-truth-test.md?metric=3D%20AP%400.5%20(0-50m)>): Higher is better; unit: PERCENT.

- [3D AP@0.5 (50-100m)](<https://www.sota2.com/research/sota/3d-object-detection-on-radial-refined-3d-ground-truth-test.md?metric=3D%20AP%400.5%20(50-100m)>): Higher is better; unit: PERCENT.

- [ATE](<https://www.sota2.com/research/sota/3d-object-detection-on-radial-refined-3d-ground-truth-test.md?metric=ATE>): Lower is better; unit: SCALAR.

- [ASE](<https://www.sota2.com/research/sota/3d-object-detection-on-radial-refined-3d-ground-truth-test.md?metric=ASE>): Lower is better; unit: SCALAR.

- [AOE](<https://www.sota2.com/research/sota/3d-object-detection-on-radial-refined-3d-ground-truth-test.md?metric=AOE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | 3D AP@0.5 Overall | Result date | Report paper |
| --- | --- | --- | --- |
| LiDAR & Camera Baseline | 68.36 | Not recorded | 68fa712b1e209131cea4faad |
| LiDAR Baseline | 62.69 | Not recorded | 68fa712b1e209131cea4faad |
| EchoFusion | 39.81 | Not recorded | 68fa712b1e209131cea4faad |

### LiDAR & Camera Baseline

3D AP@0.5 Overall: 68.36. Result ID: 69919fe13a6c3148490976d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa712b1e209131cea4faad.md>)

Recorded evaluation configuration: {"Modality":"LiDAR & Camera (L&C)"}. This record does not assert independent reproduction.

### LiDAR Baseline

3D AP@0.5 Overall: 62.69. Result ID: 69919fe13a6c3148490976d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa712b1e209131cea4faad.md>)

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

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

Recorded evaluation configuration: {"Modality":"LiDAR (L)"}. This record does not assert independent reproduction.

### EchoFusion

3D AP@0.5 Overall: 39.81. Result ID: 69919fe13a6c3148490976d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa712b1e209131cea4faad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa712b1e209131cea4faad.md>)

[Implementation](<https://github.com/tusen-ai/EchoFusion>)

Recorded evaluation configuration: {"Modality":"Radar-time & Camera (RT&C)"}. This record does not assert independent reproduction.

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