# Dense BEV segmentation on LiDAR (Holdout)

Source: [Dense BEV segmentation on LiDAR (Holdout)](<https://www.sota2.com/research/sota/dense-bev-segmentation-on-lidar-holdout>)

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

Data updated: 2026-04-23T06:16:46.112Z

Evaluation of dense Bird's Eye View (BEV) segmentation performance using LiDAR data on the specified holdout set, reporting class-specific IoU 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 | Dense BEV segmentation |
| Dataset (including any stated split) | LiDAR (Holdout) |
| Metric | mIoU (All Classes) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [mIoU (All Classes)](<https://www.sota2.com/research/sota/dense-bev-segmentation-on-lidar-holdout.md?metric=mIoU%20(All%20Classes)>): Higher is better; unit: PERCENT.

- [mIoU (Static)](<https://www.sota2.com/research/sota/dense-bev-segmentation-on-lidar-holdout.md?metric=mIoU%20(Static)>): Higher is better; unit: PERCENT.

- [IoU (Vehicles)](<https://www.sota2.com/research/sota/dense-bev-segmentation-on-lidar-holdout.md?metric=IoU%20(Vehicles)>): Higher is better; unit: PERCENT.

- [IoU (VRU)](<https://www.sota2.com/research/sota/dense-bev-segmentation-on-lidar-holdout.md?metric=IoU%20(VRU)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU (All Classes) | Result date | Report paper |
| --- | --- | --- | --- |
| SegF. (EP.) | 69 | Not recorded | 69e85bf07d0172140ec8121a |
| SegF. (Int.) | 65.6 | Not recorded | 69e85bf07d0172140ec8121a |
| SegF. | 44.2 | Not recorded | 69e85bf07d0172140ec8121a |
| Diff. | 43.7 | Not recorded | 69e85bf07d0172140ec8121a |
| SegF. | 42.6 | Not recorded | 69e85bf07d0172140ec8121a |
| SegF. | 16.8 | Not recorded | 69e85bf07d0172140ec8121a |

### SegF. (EP.)

mIoU (All Classes): 69. Result ID: 69e9b8ad47f34ce924d03902.

[Reporting paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

Recorded evaluation configuration: {"Input":"C+L","LiDAR fine-tuning":"true"}. This record does not assert independent reproduction.

### SegF. (Int.)

mIoU (All Classes): 65.6. Result ID: 69e9b8ad47f34ce924d03901.

[Reporting paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

Recorded evaluation configuration: {"Input":"C+L","LiDAR fine-tuning":"true"}. This record does not assert independent reproduction.

### SegF.

mIoU (All Classes): 44.2. Result ID: 69e9b8ad47f34ce924d03900.

[Reporting paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

Recorded evaluation configuration: {"Input":"C+L","LiDAR fine-tuning":"false"}. This record does not assert independent reproduction.

### Diff.

mIoU (All Classes): 43.7. Result ID: 69e9b8ad47f34ce924d03903.

[Reporting paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

Recorded evaluation configuration: {"Input":"C+L","LiDAR fine-tuning":"false"}. This record does not assert independent reproduction.

### SegF.

mIoU (All Classes): 42.6. Result ID: 69e9b8ad47f34ce924d038fe.

[Reporting paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

Recorded evaluation configuration: {"Input":"L","LiDAR fine-tuning":"N/A"}. This record does not assert independent reproduction.

### SegF.

mIoU (All Classes): 16.8. Result ID: 69e9b8ad47f34ce924d038ff.

[Reporting paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85bf07d0172140ec8121a.md>)

Recorded evaluation configuration: {"Input":"C","LiDAR fine-tuning":"N/A"}. This record does not assert independent reproduction.

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