# Open-vocabulary 3D Semantic Segmentation on Replica Average

Source: [Open-vocabulary 3D Semantic Segmentation on Replica Average](<https://www.sota2.com/research/sota/open-vocabulary-3d-semantic-segmentation-on-replica-average>)

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

Data updated: 2026-03-18T08:31:53.774Z

Evaluation of Open-vocabulary 3D Semantic Segmentation performance on the Replica Average configuration, reporting mIoU, F-mIoU, and mAcc.

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 | Open-vocabulary 3D Semantic Segmentation |
| Dataset (including any stated split) | Replica Average |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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/open-vocabulary-3d-semantic-segmentation-on-replica-average.md?metric=mIoU>): Higher is better; unit: PERCENT.

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

- [mAcc](<https://www.sota2.com/research/sota/open-vocabulary-3d-semantic-segmentation-on-replica-average.md?metric=mAcc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| OGScene3D | 30.16 | Not recorded | 69ba31830636e5bf4afc0765 |
| HOV-SG | 23.05 | Not recorded | 69ba31830636e5bf4afc0765 |
| ConceptGraphs | 14.95 | Not recorded | 69ba31830636e5bf4afc0765 |

### OGScene3D

mIoU: 30.16. Result ID: 69ba62dc47f34ce924a445d3.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31830636e5bf4afc0765.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31830636e5bf4afc0765.md>)

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

### HOV-SG

mIoU: 23.05. Result ID: 69ba62dc47f34ce924a445d2.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31830636e5bf4afc0765.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f71e209131cea64e5a.md>)

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

### ConceptGraphs

mIoU: 14.95. Result ID: 69ba62dc47f34ce924a445d1.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31830636e5bf4afc0765.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cdcf.md>)

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.