# Object Detection on S3DIS furniture subclass (Building 5)

Source: [Object Detection on S3DIS furniture subclass (Building 5)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5>)

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

Data updated: 2026-02-26T05:23:09.279Z

Evaluation of Object Detection performance on the specific furniture subclass subset within Building 5 of the S3DIS dataset, reporting per-class Average Precision (AP) and Recall.

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 | Object Detection |
| Dataset (including any stated split) | S3DIS furniture subclass (Building 5) |
| Metric | AP (Table) |
| 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

- [AP (Table)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=AP%20(Table)>): Higher is better; unit: PERCENT.

- [AP (Chair)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=AP%20(Chair)>): Higher is better; unit: PERCENT.

- [AP (Sofa)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=AP%20(Sofa)>): Higher is better; unit: PERCENT.

- [AP (Bookcase)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=AP%20(Bookcase)>): Higher is better; unit: PERCENT.

- [AP (Board)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=AP%20(Board)>): Higher is better; unit: PERCENT.

- [Avg AP](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=Avg%20AP>): Higher is better; unit: PERCENT.

- [Recall (Table)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=Recall%20(Table)>): Higher is better; unit: PERCENT.

- [Recall (Chair)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=Recall%20(Chair)>): Higher is better; unit: PERCENT.

- [Recall (Sofa)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=Recall%20(Sofa)>): Higher is better; unit: PERCENT.

- [Recall (Bookcase)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=Recall%20(Bookcase)>): Higher is better; unit: PERCENT.

- [Recall (Board)](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=Recall%20(Board)>): Higher is better; unit: PERCENT.

- [Avg Recall](<https://www.sota2.com/research/sota/object-detection-on-s3dis-furniture-subclass-building-5.md?metric=Avg%20Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP (Table) | Result date | Report paper |
| --- | --- | --- | --- |
| GSDN | 73.69 | Not recorded | 68fa67c71e209131cea183f0 |
| GSDN | 36.57 | Not recorded | 68fa67c71e209131cea183f0 |
| Yang et al. | 27.33 | Not recorded | 68fa67c71e209131cea183f0 |
| Yang et al. | 4.02 | Not recorded | 68fa67c71e209131cea183f0 |

### GSDN

AP (Table): 73.69. Result ID: 698d43b38b517eb43320337a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67c71e209131cea183f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67c71e209131cea183f0.md>)

Recorded evaluation configuration: {"IoU Threshold":0.25}. This record does not assert independent reproduction.

### GSDN

AP (Table): 36.57. Result ID: 698d43b38b517eb43320337c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67c71e209131cea183f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67c71e209131cea183f0.md>)

Recorded evaluation configuration: {"IoU Threshold":0.5}. This record does not assert independent reproduction.

### Yang et al.

AP (Table): 27.33. Result ID: 698d43b38b517eb433203379.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67c71e209131cea183f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa665a1e209131cea0fbdd.md>)

[Implementation](<https://github.com/Yang7879/3D-BoNet>)

Recorded evaluation configuration: {"IoU Threshold":0.25,"Source type":"Converted instance segmentation results to bounding boxes"}. This record does not assert independent reproduction.

### Yang et al.

AP (Table): 4.02. Result ID: 698d43b38b517eb43320337b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67c71e209131cea183f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa665a1e209131cea0fbdd.md>)

[Implementation](<https://github.com/Yang7879/3D-BoNet>)

Recorded evaluation configuration: {"IoU Threshold":0.5,"Source type":"Converted instance segmentation results to bounding boxes"}. This record does not assert independent reproduction.

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