# Semantic Segmentation on S3DIS (Area 6)

Source: [Semantic Segmentation on S3DIS (Area 6)](<https://www.sota2.com/research/sota/semantic-segmentation-on-s3dis-area-6>)

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

Data updated: 2026-02-26T06:10:34.757Z

Evaluation of Semantic Segmentation performance specifically on Area 6 of the Stanford Indoor Dataset (S3DIS).

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) | S3DIS (Area 6) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/semantic-segmentation-on-s3dis-area-6.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-s3dis-area-6.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Overall Acc](<https://www.sota2.com/research/sota/semantic-segmentation-on-s3dis-area-6.md?metric=Overall%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| PonderV2 | 87.4 | Not recorded | 68fa78111e209131cea7699b |
| PPT | 86.4 | Not recorded | 68fa78111e209131cea7699b |
| DGCNN (Ours) | 63.52 | Not recorded | 68fa68651e209131cea1bc73 |
| DGCNN (Random Init) | 63.48 | Not recorded | 68fa68651e209131cea1bc73 |
| DGCNN (VoxelSSL) | 60.65 | Not recorded | 68fa68651e209131cea1bc73 |

### PonderV2

mIoU: 87.4. Result ID: 69957aea3badfaffe671f19a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78111e209131cea7699b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78111e209131cea7699b.md>)

[Implementation](<https://github.com/OpenGVLab/PonderV2>)

Recorded evaluation configuration: {"Pre-training strategy":"PonderV2"}. This record does not assert independent reproduction.

### PPT

mIoU: 86.4. Result ID: 69957aea3badfaffe671f199.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78111e209131cea7699b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74351e209131cea606f6.md>)

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

Recorded evaluation configuration: {"Pre-training strategy":"PPT"}. This record does not assert independent reproduction.

### DGCNN (Ours)

mIoU: 63.52. Result ID: 698d6cc38b517eb43321683a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68651e209131cea1bc73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68651e209131cea1bc73.md>)

Recorded evaluation configuration: {"Pre-training":"Self-supervised (Ours)","Few-shot Setting":"5-way 10-shot","Backbone":"DGCNN"}. This record does not assert independent reproduction.

### DGCNN (Random Init)

mIoU: 63.48. Result ID: 698d6cc38b517eb433216838.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68651e209131cea1bc73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e11e209131cea0d1ac.md>)

[Implementation](<https://github.com/WangYueFt/dgcnn>)

Recorded evaluation configuration: {"Pre-training":"None","Few-shot Setting":"5-way 10-shot","Backbone":"DGCNN"}. This record does not assert independent reproduction.

### DGCNN (VoxelSSL)

mIoU: 60.65. Result ID: 698d6cc38b517eb433216839.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68651e209131cea1bc73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65dd1e209131cea0ced1.md>)

Recorded evaluation configuration: {"Pre-training":"VoxelSSL","Few-shot Setting":"5-way 10-shot","Backbone":"DGCNN"}. This record does not assert independent reproduction.

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