# Monocular 3D Object Detection (Car) on KITTI official (test)

Source: [Monocular 3D Object Detection (Car) on KITTI official (test)](<https://www.sota2.com/research/sota/monocular-3d-object-detection-car-on-kitti-official-test>)

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

Data updated: 2026-02-26T05:23:15.307Z

Evaluation of Monocular 3D Object Detection performance specifically for the 'Car' class on the official KITTI test set, reporting 3D Average Precision (AP3D) and Bird's Eye View Average Precision (APBEV) 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 | Monocular 3D Object Detection (Car) |
| Dataset (including any stated split) | KITTI official (test) |
| Metric | AP3D (Easy) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [AP3D (Easy)](<https://www.sota2.com/research/sota/monocular-3d-object-detection-car-on-kitti-official-test.md?metric=AP3D%20(Easy)>): Higher is better; unit: PERCENT.

- [AP3D (Moderate)](<https://www.sota2.com/research/sota/monocular-3d-object-detection-car-on-kitti-official-test.md?metric=AP3D%20(Moderate)>): Higher is better; unit: PERCENT.

- [AP3D (Hard)](<https://www.sota2.com/research/sota/monocular-3d-object-detection-car-on-kitti-official-test.md?metric=AP3D%20(Hard)>): Higher is better; unit: PERCENT.

- [APBEV (Easy)](<https://www.sota2.com/research/sota/monocular-3d-object-detection-car-on-kitti-official-test.md?metric=APBEV%20(Easy)>): Higher is better; unit: PERCENT.

- [APBEV (Moderate)](<https://www.sota2.com/research/sota/monocular-3d-object-detection-car-on-kitti-official-test.md?metric=APBEV%20(Moderate)>): Higher is better; unit: PERCENT.

- [APBEV (Hard)](<https://www.sota2.com/research/sota/monocular-3d-object-detection-car-on-kitti-official-test.md?metric=APBEV%20(Hard)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP3D (Easy) | Result date | Report paper |
| --- | --- | --- | --- |
| Pseudo-Stereo (Ours-fld) | 23.74 | Not recorded | 68fa6bf71e209131cea314b4 |
| Pseudo-Stereo (Ours-fcd) | 23.61 | Not recorded | 68fa6bf71e209131cea314b4 |
| DD3D | 23.22 | Not recorded | 68fa6bf71e209131cea314b4 |
| MonoEF | 21.29 | Not recorded | 68fa6bf71e209131cea314b4 |
| MonoFlex | 19.94 | Not recorded | 68fa6bf71e209131cea314b4 |
| Pseudo-Stereo (Ours-im) | 19.79 | Not recorded | 68fa6bf71e209131cea314b4 |
| DDMP-3D | 19.71 | Not recorded | 68fa6bf71e209131cea314b4 |
| MonoRUn | 19.65 | Not recorded | 68fa6bf71e209131cea314b4 |
| DFR-Net | 19.4 | Not recorded | 68fa6bf71e209131cea314b4 |
| CaDDN | 19.17 | Not recorded | 68fa6bf71e209131cea314b4 |
| MonoRCNN | 18.36 | Not recorded | 68fa6bf71e209131cea314b4 |
| GrooMeD-NMS | 18.1 | Not recorded | 68fa6bf71e209131cea314b4 |
| D4LCN | 16.65 | Not recorded | 68fa6bf71e209131cea314b4 |
| AM3D | 16.5 | Not recorded | 68fa6bf71e209131cea314b4 |
| M3D-RPN | 14.76 | Not recorded | 68fa6bf71e209131cea314b4 |
| MonoPair | 13.04 | Not recorded | 68fa6bf71e209131cea314b4 |
| MonoDIS | 10.37 | Not recorded | 68fa6bf71e209131cea314b4 |

### Pseudo-Stereo (Ours-fld)

AP3D (Easy): 23.74. Result ID: 698eafd5ffc3901de09fcdea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Implementation](<https://github.com/revisitq/Pseudo-Stereo-3D>)

Recorded evaluation configuration: {"Variant":"feature-level generation","Depth Loss":true}. This record does not assert independent reproduction.

### Pseudo-Stereo (Ours-fcd)

AP3D (Easy): 23.61. Result ID: 698eafd5ffc3901de09fcdeb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Implementation](<https://github.com/revisitq/Pseudo-Stereo-3D>)

Recorded evaluation configuration: {"Variant":"feature-clone","Depth Loss":true}. This record does not assert independent reproduction.

### DD3D

AP3D (Easy): 23.22. Result ID: 698eafd5ffc3901de09fcde8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a941e209131cea2908b.md>)

Recorded evaluation configuration: {"Reference":"ICCV 2021"}. This record does not assert independent reproduction.

### MonoEF

AP3D (Easy): 21.29. Result ID: 698eafd5ffc3901de09fcde1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9d.md>)

Recorded evaluation configuration: {"Reference":"CVPR 2021"}. This record does not assert independent reproduction.

### MonoFlex

AP3D (Easy): 19.94. Result ID: 698eafd5ffc3901de09fcde0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ad1e209131cea234cb.md>)

[Implementation](<https://github.com/zhangyp15/MonoFlex>)

Recorded evaluation configuration: {"Reference":"CVPR 2021"}. This record does not assert independent reproduction.

### Pseudo-Stereo (Ours-im)

AP3D (Easy): 19.79. Result ID: 698eafd5ffc3901de09fcde9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Implementation](<https://github.com/revisitq/Pseudo-Stereo-3D>)

Recorded evaluation configuration: {"Variant":"image-level generation","Depth Loss":false}. This record does not assert independent reproduction.

### DDMP-3D

AP3D (Easy): 19.71. Result ID: 698eafd5ffc3901de09fcde4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22ff8.md>)

[Implementation](<https://github.com/fudan-zvg/DDMP>)

Recorded evaluation configuration: {"Reference":"CVPR 2021"}. This record does not assert independent reproduction.

### MonoRUn

AP3D (Easy): 19.65. Result ID: 698eafd5ffc3901de09fcde5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69911e209131cea22b7d.md>)

[Implementation](<https://github.com/tjiiv-cprg/MonoRUn>)

Recorded evaluation configuration: {"Reference":"CVPR 2021"}. This record does not assert independent reproduction.

### DFR-Net

AP3D (Easy): 19.4. Result ID: 698eafd5ffc3901de09fcde6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7d1e209131cea2e8ac.md>)

Recorded evaluation configuration: {"Reference":"ICCV 2021"}. This record does not assert independent reproduction.

### CaDDN

AP3D (Easy): 19.17. Result ID: 698eafd5ffc3901de09fcde3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69911e209131cea22b69.md>)

Recorded evaluation configuration: {"Reference":"CVPR 2021"}. This record does not assert independent reproduction.

### MonoRCNN

AP3D (Easy): 18.36. Result ID: 698eafd5ffc3901de09fcde7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce51e209131cea3699f.md>)

[Implementation](<https://github.com/Rock-100/MonoDet>)

Recorded evaluation configuration: {"Reference":"ICCV 2021"}. This record does not assert independent reproduction.

### GrooMeD-NMS

AP3D (Easy): 18.1. Result ID: 698eafd5ffc3901de09fcde2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ad1e209131cea234d2.md>)

[Implementation](<https://github.com/abhi1kumar/groomed_nms>)

Recorded evaluation configuration: {"Reference":"CVPR 2021"}. This record does not assert independent reproduction.

### D4LCN

AP3D (Easy): 16.65. Result ID: 698eafd5ffc3901de09fcdde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ca1e209131cea124a5.md>)

[Implementation](<https://github.com/dingmyu/D4LCN>)

Recorded evaluation configuration: {"Reference":"CVPR 2020"}. This record does not assert independent reproduction.

### AM3D

AP3D (Easy): 16.5. Result ID: 698eafd5ffc3901de09fcddc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69981e209131cea22ed9.md>)

Recorded evaluation configuration: {"Reference":"ICCV 2019"}. This record does not assert independent reproduction.

### M3D-RPN

AP3D (Easy): 14.76. Result ID: 698eafd5ffc3901de09fcddd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa663a1e209131cea0ef88.md>)

[Implementation](<http://cvlab.cse.msu.edu/project-m3d-rpn.html>)

Recorded evaluation configuration: {"Reference":"ICCV 2019"}. This record does not assert independent reproduction.

### MonoPair

AP3D (Easy): 13.04. Result ID: 698eafd5ffc3901de09fcddf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67221e209131cea14918.md>)

Recorded evaluation configuration: {"Reference":"CVPR 2020"}. This record does not assert independent reproduction.

### MonoDIS

AP3D (Easy): 10.37. Result ID: 698eafd5ffc3901de09fcddb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65da1e209131cea0cd01.md>)

Recorded evaluation configuration: {"Reference":"ICCV 2019"}. This record does not assert independent reproduction.

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