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

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

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

Data updated: 2026-02-26T05:47:28.890Z

Evaluation of 3D Semantic Segmentation performance on the SemanticPOSS (POSS-3^3) dataset subset, reporting class-specific Intersection over Union (IoU) for 13 categories (e.g., bike, car, person) and aggregated metrics including mIoU (Novel), mIoU (Base), and mIoU (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-3^3) |
| Metric | IoU (bike) |
| 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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

## Recorded results

| Method | IoU (bike) | Result date | Report paper |
| --- | --- | --- | --- |
| EUMS | 41.17 | Not recorded | 68fa6ed41e209131cea4275a |
| NOPS | 38.55 | Not recorded | 68fa6ed41e209131cea4275a |

### EUMS

IoU (bike): 41.17. Result ID: 6990620b3a6c31484900269d.

[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

IoU (bike): 38.55. Result ID: 6990620b3a6c31484900269e.

[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.