# Bird's Eye View Object Detection on KITTI Cyclist (test)

Source: [Bird's Eye View Object Detection on KITTI Cyclist (test)](<https://www.sota2.com/research/sota/bird-s-eye-view-object-detection-on-kitti-cyclist-test>)

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

Data updated: 2026-02-26T05:23:30.601Z

Evaluation of Bird's Eye View (BEV) Object Detection performance specifically for Cyclists on the test split of the KITTI dataset, reporting Average Precision (AP\_BEV) 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 | Bird's Eye View Object Detection |
| Dataset (including any stated split) | KITTI Cyclist (test) |
| Metric | AP\_BEV (Easy) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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\_BEV (Easy)](<https://www.sota2.com/research/sota/bird-s-eye-view-object-detection-on-kitti-cyclist-test.md?metric=AP_BEV%20(Easy)>): Higher is better; unit: PERCENT.

- [AP\_BEV (Moderate)](<https://www.sota2.com/research/sota/bird-s-eye-view-object-detection-on-kitti-cyclist-test.md?metric=AP_BEV%20(Moderate)>): Higher is better; unit: PERCENT.

- [AP\_BEV (Hard)](<https://www.sota2.com/research/sota/bird-s-eye-view-object-detection-on-kitti-cyclist-test.md?metric=AP_BEV%20(Hard)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP\_BEV (Easy) | Result date | Report paper |
| --- | --- | --- | --- |
| STD | 81.04 | Not recorded | 68fa66111e209131cea0e044 |
| PointPillars | 79.14 | Not recorded | 68fa66111e209131cea0e044 |
| F-PointNet | 75.38 | Not recorded | 68fa66111e209131cea0e044 |
| SECOND | 73.67 | Not recorded | 68fa66111e209131cea0e044 |
| AVOD-FPN | 68.09 | Not recorded | 68fa66111e209131cea0e044 |
| VoxelNet | 66.7 | Not recorded | 68fa66111e209131cea0e044 |
| AVOD | 63.66 | Not recorded | 68fa66111e209131cea0e044 |

### STD

AP\_BEV (Easy): 81.04. Result ID: 698cd7de8b517eb4331d1e55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

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

### PointPillars

AP\_BEV (Easy): 79.14. Result ID: 698cd7de8b517eb4331d1e54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

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

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

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

### F-PointNet

AP\_BEV (Easy): 75.38. Result ID: 698cd7de8b517eb4331d1e50.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03af0.md>)

Recorded evaluation configuration: {"Modality":"RGB + LiDAR"}. This record does not assert independent reproduction.

### SECOND

AP\_BEV (Easy): 73.67. Result ID: 698cd7de8b517eb4331d1e53.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

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

### AVOD-FPN

AP\_BEV (Easy): 68.09. Result ID: 698cd7de8b517eb4331d1e51.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649d1e209131cea059ea.md>)

[Implementation](<https://github.com/kujason/avod>)

Recorded evaluation configuration: {"Modality":"RGB + LiDAR"}. This record does not assert independent reproduction.

### VoxelNet

AP\_BEV (Easy): 66.7. Result ID: 698cd7de8b517eb4331d1e52.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63cd1e209131cea00bb8.md>)

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

### AVOD

AP\_BEV (Easy): 63.66. Result ID: 698cd7de8b517eb4331d1e4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66111e209131cea0e044.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649d1e209131cea059ea.md>)

[Implementation](<https://github.com/kujason/avod>)

Recorded evaluation configuration: {"Modality":"RGB + LiDAR"}. This record does not assert independent reproduction.

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