# LiDAR-based localization on Oxford RobotCar PointNetVLAD-split (test)

Source: [LiDAR-based localization on Oxford RobotCar PointNetVLAD-split (test)](<https://www.sota2.com/research/sota/lidar-based-localization-on-oxford-robotcar-pointnetvlad-split-test>)

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

Data updated: 2026-02-26T06:01:19.587Z

Evaluation of LiDAR-based localization performance using the PointNetVLAD test split of the Oxford RobotCar dataset, reporting retrieval recall metrics.

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 | LiDAR-based localization |
| Dataset (including any stated split) | Oxford RobotCar PointNetVLAD-split (test) |
| Metric | Recall @ 1% Threshold |
| 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

- [Recall @ 1% Threshold](<https://www.sota2.com/research/sota/lidar-based-localization-on-oxford-robotcar-pointnetvlad-split-test.md?metric=Recall%20%40%201%25%20Threshold>): Higher is better; unit: PERCENT.

- [Recall @ Rank 1](<https://www.sota2.com/research/sota/lidar-based-localization-on-oxford-robotcar-pointnetvlad-split-test.md?metric=Recall%20%40%20Rank%201>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall @ 1% Threshold | Result date | Report paper |
| --- | --- | --- | --- |
| SOE-Net | 96.43 | Not recorded | 68fa6a071e209131cea25914 |
| DAGC | 87.78 | Not recorded | 68fa6a071e209131cea25914 |
| PCAN | 86.4 | Not recorded | 68fa6a071e209131cea25914 |

### SOE-Net

Recall @ 1% Threshold: 96.43. Result ID: 698e006dffc3901de09a0daf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Implementation](<https://github.com/Yan-Xia/SOE-Net>)

Recorded evaluation configuration: {"Training Datasets":"Oxford RobotCar, U.S. and R.A."}. This record does not assert independent reproduction.

### DAGC

Recall @ 1% Threshold: 87.78. Result ID: 698e006dffc3901de09a0db0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

Recorded evaluation configuration: {"Training Datasets":"Oxford RobotCar, U.S. and R.A."}. This record does not assert independent reproduction.

### PCAN

Recall @ 1% Threshold: 86.4. Result ID: 698e006dffc3901de09a0db1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a91e209131cea0bb54.md>)

Recorded evaluation configuration: {"Training Datasets":"Oxford RobotCar, U.S. and R.A."}. This record does not assert independent reproduction.

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