# 3D Lane Detection on 3D Lane Synthetic Dataset 2020 (test)

Source: [3D Lane Detection on 3D Lane Synthetic Dataset 2020 (test)](<https://www.sota2.com/research/sota/3d-lane-detection-on-3d-lane-synthetic-dataset-2020-test>)

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

Data updated: 2026-02-26T05:42:39.964Z

Evaluation of 3D Lane Detection performance on the test split of the 3D Lane Synthetic Dataset 2020, measured using F-Score and AP.

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 Lane Detection |
| Dataset (including any stated split) | 3D Lane Synthetic Dataset 2020 (test) |
| Metric | F-Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [F-Score](<https://www.sota2.com/research/sota/3d-lane-detection-on-3d-lane-synthetic-dataset-2020-test.md?metric=F-Score>): Higher is better; unit: PERCENT.

- [AP](<https://www.sota2.com/research/sota/3d-lane-detection-on-3d-lane-synthetic-dataset-2020-test.md?metric=AP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F-Score | Result date | Report paper |
| --- | --- | --- | --- |
| CLGo | 91.9 | Not recorded | 68fa6b871e209131cea2edf2 |
| Gen-LaneNet | 88.1 | Not recorded | 68fa6b871e209131cea2edf2 |
| CLGo | 87.3 | Not recorded | 68fa6b871e209131cea2edf2 |
| 3D-LaneNet | 86.4 | Not recorded | 68fa6b871e209131cea2edf2 |
| CLGo | 86.1 | Not recorded | 68fa6b871e209131cea2edf2 |
| Gen-LaneNet | 85.3 | Not recorded | 68fa6b871e209131cea2edf2 |
| Gen-LaneNet | 78 | Not recorded | 68fa6b871e209131cea2edf2 |
| 3D-LaneNet | 72.5 | Not recorded | 68fa6b871e209131cea2edf2 |
| 3D-LaneNet | 72 | Not recorded | 68fa6b871e209131cea2edf2 |

### CLGo

F-Score: 91.9. Result ID: 698e949bffc3901de09ed66f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Implementation](<https://github.com/liuruijin17/CLGo>)

Recorded evaluation configuration: {"FPS":75,"MACs":"0.497 GHz","#Para":"1.5 million","PP":false,"Scene":"Balanced Scenes (BS)","Camera Pose":"PD"}. This record does not assert independent reproduction.

### Gen-LaneNet

F-Score: 88.1. Result ID: 698e949bffc3901de09ed66c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c41e209131cea1e3ca.md>)

[Implementation](<https://github.com/yuliangguo/3D_Lane_Synthetic_Dataset>)

Recorded evaluation configuration: {"FPS":60,"MACs":"9.85 GHz","#Para":"3.4 million","PP":true,"Scene":"Balanced Scenes (BS)","Camera Pose":"GT"}. This record does not assert independent reproduction.

### CLGo

F-Score: 87.3. Result ID: 698e949bffc3901de09ed671.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Implementation](<https://github.com/liuruijin17/CLGo>)

Recorded evaluation configuration: {"FPS":75,"MACs":"0.497 GHz","#Para":"1.5 million","PP":false,"Scene":"Scenes with Visual Variations (SVV)","Camera Pose":"PD"}. This record does not assert independent reproduction.

### 3D-LaneNet

F-Score: 86.4. Result ID: 698e949bffc3901de09ed669.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66541e209131cea0f814.md>)

[Implementation](<https://sites.google.com/view/danlevi/3dlanes>)

Recorded evaluation configuration: {"FPS":53,"MACs":"60.47 GHz","#Para":"20.6 million","PP":true,"Scene":"Balanced Scenes (BS)","Camera Pose":"GT"}. This record does not assert independent reproduction.

### CLGo

F-Score: 86.1. Result ID: 698e949bffc3901de09ed670.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Implementation](<https://github.com/liuruijin17/CLGo>)

Recorded evaluation configuration: {"FPS":75,"MACs":"0.497 GHz","#Para":"1.5 million","PP":false,"Scene":"Rarely Observed Scenes (ROS)","Camera Pose":"PD"}. This record does not assert independent reproduction.

### Gen-LaneNet

F-Score: 85.3. Result ID: 698e949bffc3901de09ed66e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c41e209131cea1e3ca.md>)

[Implementation](<https://github.com/yuliangguo/3D_Lane_Synthetic_Dataset>)

Recorded evaluation configuration: {"FPS":60,"MACs":"9.85 GHz","#Para":"3.4 million","PP":true,"Scene":"Scenes with Visual Variations (SVV)","Camera Pose":"GT"}. This record does not assert independent reproduction.

### Gen-LaneNet

F-Score: 78. Result ID: 698e949bffc3901de09ed66d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c41e209131cea1e3ca.md>)

[Implementation](<https://github.com/yuliangguo/3D_Lane_Synthetic_Dataset>)

Recorded evaluation configuration: {"FPS":60,"MACs":"9.85 GHz","#Para":"3.4 million","PP":true,"Scene":"Rarely Observed Scenes (ROS)","Camera Pose":"GT"}. This record does not assert independent reproduction.

### 3D-LaneNet

F-Score: 72.5. Result ID: 698e949bffc3901de09ed66b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66541e209131cea0f814.md>)

[Implementation](<https://sites.google.com/view/danlevi/3dlanes>)

Recorded evaluation configuration: {"FPS":53,"MACs":"60.47 GHz","#Para":"20.6 million","PP":true,"Scene":"Scenes with Visual Variations (SVV)","Camera Pose":"GT"}. This record does not assert independent reproduction.

### 3D-LaneNet

F-Score: 72. Result ID: 698e949bffc3901de09ed66a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2edf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66541e209131cea0f814.md>)

[Implementation](<https://sites.google.com/view/danlevi/3dlanes>)

Recorded evaluation configuration: {"FPS":53,"MACs":"60.47 GHz","#Para":"20.6 million","PP":true,"Scene":"Rarely Observed Scenes (ROS)","Camera Pose":"GT"}. This record does not assert independent reproduction.

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