# 3D Object Detection on DAIR-V2X PP→SECOND

Source: [3D Object Detection on DAIR-V2X PP→SECOND](<https://www.sota2.com/research/sota/3d-object-detection-on-dair-v2x-pp-second>)

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

Data updated: 2026-05-04T08:54:33.794Z

Evaluation of 3D Object Detection performance on the DAIR-V2X dataset using the PP→SECOND configuration, reporting Average Precision (AP) at IoU thresholds of 0.30, 0.50, and 0.70.

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) | DAIR-V2X PP→SECOND |
| Metric | AP@30 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [AP@30](<https://www.sota2.com/research/sota/3d-object-detection-on-dair-v2x-pp-second.md?metric=AP%4030>): Higher is better; unit: PERCENT.

- [AP@50](<https://www.sota2.com/research/sota/3d-object-detection-on-dair-v2x-pp-second.md?metric=AP%4050>): Higher is better; unit: PERCENT.

- [AP@70](<https://www.sota2.com/research/sota/3d-object-detection-on-dair-v2x-pp-second.md?metric=AP%4070>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP@30 | Result date | Report paper |
| --- | --- | --- | --- |
| HEAL w/ base | 82.8 | Not recorded | 69f82816c0f56ed843088ac6 |
| BOLT | 72.6 | Not recorded | 69f82816c0f56ed843088ac6 |
| STAMP w/ base | 60.3 | Not recorded | 69f82816c0f56ed843088ac6 |
| HEAL w/o base | 45.9 | Not recorded | 69f82816c0f56ed843088ac6 |
| STAMP w/o base | 0 | Not recorded | 69f82816c0f56ed843088ac6 |

### HEAL w/ base

AP@30: 82.8. Result ID: 69f85e2247f34ce924dc31fc.

[Reporting paper](<https://www.sota2.com/research/paper/69f82816c0f56ed843088ac6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b91e209131cea5826d.md>)

Recorded evaluation configuration: {"Collab. Train":true,"Online":false,"Extra Params":"—"}. This record does not assert independent reproduction.

### BOLT

AP@30: 72.6. Result ID: 69f85e2247f34ce924dc31fa.

[Reporting paper](<https://www.sota2.com/research/paper/69f82816c0f56ed843088ac6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f82816c0f56ed843088ac6.md>)

Recorded evaluation configuration: {"Collab. Train":false,"Online":true,"Extra Params":"0.9M"}. This record does not assert independent reproduction.

### STAMP w/ base

AP@30: 60.3. Result ID: 69f85e2247f34ce924dc31fb.

[Reporting paper](<https://www.sota2.com/research/paper/69f82816c0f56ed843088ac6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76c31e209131cea6edad.md>)

Recorded evaluation configuration: {"Collab. Train":true,"Online":false,"Extra Params":"0.4M"}. This record does not assert independent reproduction.

### HEAL w/o base

AP@30: 45.9. Result ID: 69f85e2247f34ce924dc31f8.

[Reporting paper](<https://www.sota2.com/research/paper/69f82816c0f56ed843088ac6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b91e209131cea5826d.md>)

Recorded evaluation configuration: {"Collab. Train":false,"Online":false,"Extra Params":"—"}. This record does not assert independent reproduction.

### STAMP w/o base

AP@30: 0. Result ID: 69f85e2247f34ce924dc31f9.

[Reporting paper](<https://www.sota2.com/research/paper/69f82816c0f56ed843088ac6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76c31e209131cea6edad.md>)

Recorded evaluation configuration: {"Collab. Train":false,"Online":false,"Extra Params":"0.4M"}. This record does not assert independent reproduction.

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