# 3D Object Detection on SUNCG

Source: [3D Object Detection on SUNCG](<https://www.sota2.com/research/sota/3d-object-detection-on-suncg>)

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

Data updated: 2026-02-26T06:09:58.986Z

Evaluation of 3D object detection performance on the SUNCG dataset.

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 Object Detection |
| Dataset (including any stated split) | SUNCG |
| Metric | mAP@0.25 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [mAP@0.25](<https://www.sota2.com/research/sota/3d-object-detection-on-suncg.md?metric=mAP%400.25>): Higher is better; unit: PERCENT.

- [mAP@0.5](<https://www.sota2.com/research/sota/3d-object-detection-on-suncg.md?metric=mAP%400.5>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP@0.25 | Result date | Report paper |
| --- | --- | --- | --- |
| 3D-SIS | 32.2 | Not recorded | 68fa65ac1e209131cea0bda7 |
| 3D-SIS | 31.3 | Not recorded | 68fa65ac1e209131cea0bda7 |
| 3D-SIS | 30.9 | Not recorded | 68fa65ac1e209131cea0bda7 |
| 3D-SIS | 27.8 | Not recorded | 68fa65ac1e209131cea0bda7 |
| Frustum PointNet | 24.9 | Not recorded | 68fa65ac1e209131cea0bda7 |
| Mask R-CNN 2D-3D | 20.4 | Not recorded | 68fa65ac1e209131cea0bda7 |
| Deep Sliding Shapes | 12.8 | Not recorded | 68fa65ac1e209131cea0bda7 |

### 3D-SIS

mAP@0.25: 32.2. Result ID: 698cc30e8b517eb4331c8fcf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

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

Recorded evaluation configuration: {"Input modality":"geometry + multi-view RGB","Number of views":5}. This record does not assert independent reproduction.

### 3D-SIS

mAP@0.25: 31.3. Result ID: 698cc30e8b517eb4331c8fce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

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

Recorded evaluation configuration: {"Input modality":"geometry + multi-view RGB","Number of views":3}. This record does not assert independent reproduction.

### 3D-SIS

mAP@0.25: 30.9. Result ID: 698cc30e8b517eb4331c8fcd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

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

Recorded evaluation configuration: {"Input modality":"geometry + multi-view RGB","Number of views":1}. This record does not assert independent reproduction.

### 3D-SIS

mAP@0.25: 27.8. Result ID: 698cc30e8b517eb4331c8fcc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

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

Recorded evaluation configuration: {"Input modality":"geometry only"}. This record does not assert independent reproduction.

### Frustum PointNet

mAP@0.25: 24.9. Result ID: 698cc30e8b517eb4331c8fcb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03af0.md>)

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

### Mask R-CNN 2D-3D

mAP@0.25: 20.4. Result ID: 698cc30e8b517eb4331c8fca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f21e209131cea01b22.md>)

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

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

### Deep Sliding Shapes

mAP@0.25: 12.8. Result ID: 698cc30e8b517eb4331c8fc9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bda7.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.
