# 3D Semantic Segmentation on SemanticKITTI-FV (val)

Source: [3D Semantic Segmentation on SemanticKITTI-FV (val)](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semantickitti-fv-val>)

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

Data updated: 2026-02-26T06:10:29.762Z

Evaluation of 3D Semantic Segmentation performance on the Front View (FV) subset of the SemanticKITTI validation split, reporting overall Mean Intersection over Union (mIoU) and per-class IoU scores.

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 Semantic Segmentation |
| Dataset (including any stated split) | SemanticKITTI-FV (val) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semantickitti-fv-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

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

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

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

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

- [Other Vehicle IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semantickitti-fv-val.md?metric=Other%20Vehicle%20IoU>): Higher is better; unit: PERCENT.

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

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

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

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

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

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

- [Other Ground IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semantickitti-fv-val.md?metric=Other%20Ground%20IoU>): Higher is better; unit: PERCENT.

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

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

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

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

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

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

- [Traffic Sign IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semantickitti-fv-val.md?metric=Traffic%20Sign%20IoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| 2DPASS | 0.668 | Not recorded | 68fa74c51e209131cea63b10 |
| EPMF | 0.659 | Not recorded | 68fa74c51e209131cea63b10 |
| Cylinder3D | 0.649 | Not recorded | 68fa74c51e209131cea63b10 |
| PMF | 0.639 | Not recorded | 68fa74c51e209131cea63b10 |
| SPVNAS | 0.623 | Not recorded | 68fa74c51e209131cea63b10 |
| 2DPASS | 0.618 | Not recorded | 68fa74c51e209131cea63b10 |
| SalsaNext | 0.594 | Not recorded | 68fa74c51e209131cea63b10 |
| Uni-modal baseline | 0.586 | Not recorded | 68fa74c51e209131cea63b10 |
| MinkowskiNet | 0.585 | Not recorded | 68fa74c51e209131cea63b10 |
| RGBAL | 0.562 | Not recorded | 68fa74c51e209131cea63b10 |
| PointPainting | 0.545 | Not recorded | 68fa74c51e209131cea63b10 |
| SequeezeSegV3 | 0.533 | Not recorded | 68fa74c51e209131cea63b10 |
| RangeNet++ | 0.512 | Not recorded | 68fa74c51e209131cea63b10 |
| RandLANet | 0.5 | Not recorded | 68fa74c51e209131cea63b10 |
| SequeezeSegV2 | 0.408 | Not recorded | 68fa74c51e209131cea63b10 |

### 2DPASS

mIoU: 0.668. Result ID: 699366ab3a6c31484915ab98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dac1e209131cea3b618.md>)

[Implementation](<https://github.com/yanx27/2DPASS>)

Recorded evaluation configuration: {"Modality":"Fusion-based"}. This record does not assert independent reproduction.

### EPMF

mIoU: 0.659. Result ID: 699366ab3a6c31484915ab9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Implementation](<https://github.com/ICEORY/PMF>)

Recorded evaluation configuration: {"Modality":"Fusion-based"}. This record does not assert independent reproduction.

### Cylinder3D

mIoU: 0.649. Result ID: 699366ab3a6c31484915ab97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab41e209131cea29e52.md>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### PMF

mIoU: 0.639. Result ID: 699366ab3a6c31484915ab9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Implementation](<https://github.com/ICEORY/PMF>)

Recorded evaluation configuration: {"Modality":"Fusion-based"}. This record does not assert independent reproduction.

### SPVNAS

mIoU: 0.623. Result ID: 699366ab3a6c31484915ab96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682e1e209131cea1a95e.md>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### 2DPASS

mIoU: 0.618. Result ID: 699366ab3a6c31484915ab99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dac1e209131cea3b618.md>)

[Implementation](<https://github.com/yanx27/2DPASS>)

Recorded evaluation configuration: {"Modality":"Fusion-based","trained under our settings":true}. This record does not assert independent reproduction.

### SalsaNext

mIoU: 0.594. Result ID: 699366ab3a6c31484915ab94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### Uni-modal baseline

mIoU: 0.586. Result ID: 699366ab3a6c31484915ab9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Implementation](<https://github.com/ICEORY/PMF>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### MinkowskiNet

mIoU: 0.585. Result ID: 699366ab3a6c31484915ab95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65dd1e209131cea0ceeb.md>)

[Implementation](<https://github.com/StanfordVL/MinkowskiEngine>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### RGBAL

mIoU: 0.562. Result ID: 699366ab3a6c31484915ab9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66151e209131cea0e2f3.md>)

Recorded evaluation configuration: {"Modality":"Fusion-based","our implementation":true}. This record does not assert independent reproduction.

### PointPainting

mIoU: 0.545. Result ID: 699366ab3a6c31484915ab9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa677a1e209131cea16a77.md>)

Recorded evaluation configuration: {"Modality":"Fusion-based","our implementation":true}. This record does not assert independent reproduction.

### SequeezeSegV3

mIoU: 0.533. Result ID: 699366ab3a6c31484915ab93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69bc1e209131cea23e0d.md>)

[Implementation](<https://github.com/chenfengxu714/SqueezeSegV3>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### RangeNet++

mIoU: 0.512. Result ID: 699366ab3a6c31484915ab91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### RandLANet

mIoU: 0.5. Result ID: 699366ab3a6c31484915ab90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67771e209131cea16862.md>)

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

### SequeezeSegV2

mIoU: 0.408. Result ID: 699366ab3a6c31484915ab92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b10.md>)

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

Recorded evaluation configuration: {"Modality":"LiDAR-only"}. This record does not assert independent reproduction.

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