# Semantic Segmentation on Stanford-2D-3D-Semantic

Source: [Semantic Segmentation on Stanford-2D-3D-Semantic](<https://www.sota2.com/research/sota/semantic-segmentation-on-stanford-2d-3d-semantic>)

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

Data updated: 2026-02-26T05:45:59.468Z

Evaluation of Semantic Segmentation performance on the Stanford-2D-3D-Semantic dataset, reporting Global Accuracy, Mean Accuracy, and mIoU.

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 | Semantic Segmentation |
| Dataset (including any stated split) | Stanford-2D-3D-Semantic |
| Metric | Global Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

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

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

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

## Recorded results

| Method | Global Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| 3M2RNet | 79.8 | Not recorded | 68fa66d11e209131cea1292f |
| MMAF-Net-152 | 76.5 | Not recorded | 68fa66d11e209131cea1292f |
| D-CNN | 65.4 | Not recorded | 68fa66d11e209131cea1292f |
| DeepLab | 64.3 | Not recorded | 68fa66d11e209131cea1292f |

### 3M2RNet

Global Accuracy: 79.8. Result ID: 698d0a008b517eb4331e8a8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1292f.md>)

Recorded evaluation configuration: {"Modality":"RGB-D","multi-scale evaluation":true}. This record does not assert independent reproduction.

### MMAF-Net-152

Global Accuracy: 76.5. Result ID: 698d0a008b517eb4331e8a8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1292f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1292f.md>)

Recorded evaluation configuration: {"Modality":"RGB-D","multi-scale evaluation":false}. This record does not assert independent reproduction.

### D-CNN

Global Accuracy: 65.4. Result ID: 698d0a008b517eb4331e8a8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1292f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64251e209131cea02daf.md>)

Recorded evaluation configuration: {"Modality":"RGB-D","multi-scale evaluation":false}. This record does not assert independent reproduction.

### DeepLab

Global Accuracy: 64.3. Result ID: 698d0a008b517eb4331e8a8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1292f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62861e209131ce9f9e83.md>)

[Implementation](<https://bitbucket.org/deeplab/deeplab-public>)

Recorded evaluation configuration: {"Modality":"RGB-D","multi-scale evaluation":false}. This record does not assert independent reproduction.

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