# 3D Object Detection on SUN-RGBD common categories

Source: [3D Object Detection on SUN-RGBD common categories](<https://www.sota2.com/research/sota/3d-object-detection-on-sun-rgbd-common-categories>)

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

Data updated: 2026-02-26T05:23:14.844Z

Evaluation of 3D object detection performance specifically on the 'common categories' subset of the SUN RGB-D dataset, reporting AP3D scores.

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) | SUN-RGBD common categories |
| Metric | AP3D |
| 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

- [AP3D](<https://www.sota2.com/research/sota/3d-object-detection-on-sun-rgbd-common-categories.md?metric=AP3D>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP3D | Result date | Report paper |
| --- | --- | --- | --- |
| 3DiffTection | 38.8 | Not recorded | 68fa711e1e209131cea4f368 |
| Cube-RCNN | 35.4 | Not recorded | 68fa711e1e209131cea4f368 |
| ImVoxelNet | 30.6 | Not recorded | 68fa711e1e209131cea4f368 |
| Total3D | 27.7 | Not recorded | 68fa711e1e209131cea4f368 |

### 3DiffTection

AP3D: 38.8. Result ID: 6991b2643a6c31484909fc0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa711e1e209131cea4f368.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa711e1e209131cea4f368.md>)

[Implementation](<https://research.nvidia.com/labs/toronto-ai/3difftection/>)

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

### Cube-RCNN

AP3D: 35.4. Result ID: 6991b2643a6c31484909fc09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa711e1e209131cea4f368.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee21e209131cea42a09.md>)

[Implementation](<https://github.com/facebookresearch/omni3d>)

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

### ImVoxelNet

AP3D: 30.6. Result ID: 6991b2643a6c31484909fc08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa711e1e209131cea4f368.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b101e209131cea2be2f.md>)

[Implementation](<https://github.com/saic-vul/imvoxelnet>)

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

### Total3D

AP3D: 27.7. Result ID: 6991b2643a6c31484909fc07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa711e1e209131cea4f368.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67211e209131cea1482a.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.