# 3D Semantic Segmentation on SemanticPOSS (POSS-3^2)

Source: [3D Semantic Segmentation on SemanticPOSS (POSS-3^2)](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2>)

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

Data updated: 2026-02-26T05:37:48.528Z

Evaluation of 3D Semantic Segmentation performance on the SemanticPOSS (POSS-3^2) dataset, reporting class-specific Intersection over Union (IoU) metrics for various categories (e.g., bike, car, rider) and overall mean IoU (mIoU Novel, Base, All).

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) | SemanticPOSS (POSS-3^2) |
| Metric | Bike IoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Bike IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Bike%20IoU>): Higher is better; unit: PERCENT.

- [Building IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Building%20IoU>): Higher is better; unit: PERCENT.

- [Car IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Car%20IoU>): Higher is better; unit: PERCENT.

- [Cone IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Cone%20IoU>): Higher is better; unit: PERCENT.

- [Fence IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Fence%20IoU>): Higher is better; unit: PERCENT.

- [Ground IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Ground%20IoU>): Higher is better; unit: PERCENT.

- [Person IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Person%20IoU>): Higher is better; unit: PERCENT.

- [Plants IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Plants%20IoU>): Higher is better; unit: PERCENT.

- [Pole IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Pole%20IoU>): Higher is better; unit: PERCENT.

- [Rider IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Rider%20IoU>): Higher is better; unit: PERCENT.

- [Traffic IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Traffic%20IoU>): Higher is better; unit: PERCENT.

- [Trash Can IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Trash%20Can%20IoU>): Higher is better; unit: PERCENT.

- [Trunk IoU](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=Trunk%20IoU>): Higher is better; unit: PERCENT.

- [mIoU (Novel)](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=mIoU%20(Novel)>): Higher is better; unit: PERCENT.

- [mIoU (Base)](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=mIoU%20(Base)>): Higher is better; unit: PERCENT.

- [mIoU (All)](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-semanticposs-poss-3-2.md?metric=mIoU%20(All)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Bike IoU | Result date | Report paper |
| --- | --- | --- | --- |
| EUMS | 40.14 | Not recorded | 68fa6ed41e209131cea4275a |
| NOPS | 37.16 | Not recorded | 68fa6ed41e209131cea4275a |

### EUMS

Bike IoU: 40.14. Result ID: 6990620b3a6c31484900269b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ed41e209131cea4275a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32537.md>)

Recorded evaluation configuration: {"baseline":"described in Sec. 4"}. This record does not assert independent reproduction.

### NOPS

Bike IoU: 37.16. Result ID: 6990620b3a6c31484900269c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ed41e209131cea4275a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ed41e209131cea4275a.md>)

[Implementation](<https://github.com/LuigiRiz/NOPS>)

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

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