# Cyclist 3D Object Detection on KITTI (val)

Source: [Cyclist 3D Object Detection on KITTI (val)](<https://www.sota2.com/research/sota/cyclist-3d-object-detection-on-kitti-val>)

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

Data updated: 2026-02-26T05:23:12.453Z

Evaluation of 3D Object Detection performance specifically for the Cyclist class on the KITTI validation set, reporting Bird's Eye View Average Precision (AP\_BEV) and 3D Average Precision (AP\_3D) 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 | Cyclist 3D Object Detection |
| Dataset (including any stated split) | KITTI (val) |
| Metric | AP BEV Easy |
| 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

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

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

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

- [AP 3D Easy](<https://www.sota2.com/research/sota/cyclist-3d-object-detection-on-kitti-val.md?metric=AP%203D%20Easy>): Higher is better; unit: PERCENT.

- [AP 3D Moderate](<https://www.sota2.com/research/sota/cyclist-3d-object-detection-on-kitti-val.md?metric=AP%203D%20Moderate>): Higher is better; unit: PERCENT.

- [AP 3D Hard](<https://www.sota2.com/research/sota/cyclist-3d-object-detection-on-kitti-val.md?metric=AP%203D%20Hard>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP BEV Easy | Result date | Report paper |
| --- | --- | --- | --- |
| OC Stereo | 48.2 | Not recorded | 68fa67371e209131cea14e4f |
| PL-FP | 47.6 | Not recorded | 68fa67371e209131cea14e4f |
| PSMNet + AVOD | 36.12 | Not recorded | 68fa67371e209131cea14e4f |

### OC Stereo

AP BEV Easy: 48.2. Result ID: 698d20b78b517eb4331f357d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67371e209131cea14e4f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67371e209131cea14e4f.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PL-FP

AP BEV Easy: 47.6. Result ID: 698d20b78b517eb4331f357c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67371e209131cea14e4f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67171e209131cea140c9.md>)

[Implementation](<https://github.com/mileyan/pseudo_lidar>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PSMNet + AVOD

AP BEV Easy: 36.12. Result ID: 698d20b78b517eb4331f357b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67371e209131cea14e4f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67171e209131cea140c9.md>)

[Implementation](<https://github.com/mileyan/pseudo_lidar>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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