# 3D Object Detection on KITTI (AP11 & AP40)

Source: [3D Object Detection on KITTI (AP11 & AP40)](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40>)

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

Data updated: 2026-02-26T05:38:56.611Z

Evaluation of 3D Object Detection performance on the KITTI dataset, reporting Average Precision using both the 11-point (AP11) and 40-point (AP40) recall sampling methods, broken down by 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) | KITTI 3D Object Detection |
| Metric | Car AP11 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

- [Car AP11 Easy](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40.md?metric=Car%20AP11%20Easy>): Higher is better; unit: PERCENT.

- [Car AP11 Mod](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40.md?metric=Car%20AP11%20Mod>): Higher is better; unit: PERCENT.

- [Car AP11 Hard](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40.md?metric=Car%20AP11%20Hard>): Higher is better; unit: PERCENT.

- [Car AP40 Easy](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40.md?metric=Car%20AP40%20Easy>): Higher is better; unit: PERCENT.

- [Car AP40 Mod](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40.md?metric=Car%20AP40%20Mod>): Higher is better; unit: PERCENT.

- [Car AP40 Hard](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40.md?metric=Car%20AP40%20Hard>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Car AP11 Easy | Result date | Report paper |
| --- | --- | --- | --- |
| PointPillars | 86.35 | Not recorded | 69705db5e25ad2fa9d1ed3e0 |
| PointPillars | 75.06 | Not recorded | 69705db5e25ad2fa9d1ed3e0 |
| PointPillars | 27.29 | Not recorded | 69705db5e25ad2fa9d1ed3e0 |

### PointPillars

Car AP11 Easy: 86.35. Result ID: 6997ad515698665ec40376c9.

[Reporting paper](<https://www.sota2.com/research/paper/69705db5e25ad2fa9d1ed3e0.md>)

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

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

Recorded evaluation configuration: {"Data Type":"FP32"}. This record does not assert independent reproduction.

### PointPillars

Car AP11 Easy: 75.06. Result ID: 6997ad515698665ec40376cb.

[Reporting paper](<https://www.sota2.com/research/paper/69705db5e25ad2fa9d1ed3e0.md>)

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

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

Recorded evaluation configuration: {"Data Type":"QAT INT8"}. This record does not assert independent reproduction.

### PointPillars

Car AP11 Easy: 27.29. Result ID: 6997ad515698665ec40376ca.

[Reporting paper](<https://www.sota2.com/research/paper/69705db5e25ad2fa9d1ed3e0.md>)

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

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

Recorded evaluation configuration: {"Data Type":"PTQ INT8"}. This record does not assert independent reproduction.

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