# Semantic Segmentation on Paris-Lille-3D (test)

Source: [Semantic Segmentation on Paris-Lille-3D (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test>)

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

Data updated: 2026-02-26T05:27:37.959Z

Evaluation of Semantic Segmentation performance on the test split of the Paris-Lille-3D dataset, reporting overall Accuracy (Acc), Mean Intersection over Union (mIoU), and class-specific 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 | Semantic Segmentation |
| Dataset (including any stated split) | Paris-Lille-3D (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [IoU (ground)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(ground)>): Higher is better; unit: PERCENT.

- [IoU (building)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(building)>): Higher is better; unit: PERCENT.

- [IoU (pole)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(pole)>): Higher is better; unit: PERCENT.

- [IoU (bollard)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(bollard)>): Higher is better; unit: PERCENT.

- [IoU (trash can)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(trash%20can)>): Higher is better; unit: PERCENT.

- [IoU (barrier)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(barrier)>): Higher is better; unit: PERCENT.

- [IoU (pedestrian)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(pedestrian)>): Higher is better; unit: PERCENT.

- [IoU (vegetation)](<https://www.sota2.com/research/sota/semantic-segmentation-on-paris-lille-3d-test.md?metric=IoU%20(vegetation)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DarkNet53 | 88.9 | Not recorded | 68fa676c1e209131cea1605c |
| PolarNet | 87.5 | Not recorded | 68fa676c1e209131cea1605c |
| SqueezeSegV2 | 87.3 | Not recorded | 68fa676c1e209131cea1605c |
| UNet | 80.9 | Not recorded | 68fa676c1e209131cea1605c |

### DarkNet53

Accuracy: 88.9. Result ID: 698d33868b517eb4331fc187.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1605c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66331e209131cea0eb32.md>)

[Implementation](<https://www.sota2.com/www.semantic-kitti.org>)

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

### PolarNet

Accuracy: 87.5. Result ID: 698d33868b517eb4331fc189.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1605c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1605c.md>)

[Implementation](<https://github.com/edwardzhou130/PolarSeg>)

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

### SqueezeSegV2

Accuracy: 87.3. Result ID: 698d33868b517eb4331fc186.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1605c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64db1e209131cea06bd3.md>)

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

### UNet

Accuracy: 80.9. Result ID: 698d33868b517eb4331fc188.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1605c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61e11e209131ce9f653d.md>)

[Implementation](<http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net>)

Recorded evaluation configuration: {"Projection":"Cartesian BEV"}. This record does not assert independent reproduction.

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