# 3D Object Detection on NYU V2

Source: [3D Object Detection on NYU V2](<https://www.sota2.com/research/sota/3d-object-detection-on-nyu-v2>)

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

Data updated: 2026-02-26T05:51:46.055Z

Evaluation of 3D Object Detection performance on the NYU Depth V2 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) | NYU V2 |
| Metric | Mean AP |
| 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

- [Mean AP](<https://www.sota2.com/research/sota/3d-object-detection-on-nyu-v2.md?metric=Mean%20AP>): Higher is better; unit: PERCENT.

- [AP (bed)](<https://www.sota2.com/research/sota/3d-object-detection-on-nyu-v2.md?metric=AP%20(bed)>): Higher is better; unit: PERCENT.

- [AP (chair)](<https://www.sota2.com/research/sota/3d-object-detection-on-nyu-v2.md?metric=AP%20(chair)>): Higher is better; unit: PERCENT.

- [AP (sofa)](<https://www.sota2.com/research/sota/3d-object-detection-on-nyu-v2.md?metric=AP%20(sofa)>): Higher is better; unit: PERCENT.

- [AP (table)](<https://www.sota2.com/research/sota/3d-object-detection-on-nyu-v2.md?metric=AP%20(table)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean AP | Result date | Report paper |
| --- | --- | --- | --- |
| SGPN-CNN | 41.3 | Not recorded | 68fa65db1e209131cea0cde1 |
| Deep Sliding Shapes | 37.55 | Not recorded | 68fa65db1e209131cea0cde1 |
| SGPN | 36.25 | Not recorded | 68fa65db1e209131cea0cde1 |
| Deng and Latecki | 35.55 | Not recorded | 68fa65db1e209131cea0cde1 |

### SGPN-CNN

Mean AP: 41.3. Result ID: 698ccdc38b517eb4331cddb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65db1e209131cea0cde1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65db1e209131cea0cde1.md>)

[Implementation](<https://www.sota2.com/github.com/laughtervv/SGPN>)

Recorded evaluation configuration: {"ground\_truth\_type":"tight bounding box on points"}. This record does not assert independent reproduction.

### Deep Sliding Shapes

Mean AP: 37.55. Result ID: 698ccdc38b517eb4331cddad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65db1e209131cea0cde1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62611e209131ce9f8f21.md>)

[Implementation](<http://dss.cs.princeton.edu/>)

Recorded evaluation configuration: {"ground\_truth\_type":"large bounding box with invisible regions"}. This record does not assert independent reproduction.

### SGPN

Mean AP: 36.25. Result ID: 698ccdc38b517eb4331cddaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65db1e209131cea0cde1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65db1e209131cea0cde1.md>)

[Implementation](<https://www.sota2.com/github.com/laughtervv/SGPN>)

Recorded evaluation configuration: {"ground\_truth\_type":"tight bounding box on points"}. This record does not assert independent reproduction.

### Deng and Latecki

Mean AP: 35.55. Result ID: 698ccdc38b517eb4331cddae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65db1e209131cea0cde1.md>)

Recorded evaluation configuration: {"ground\_truth\_type":"large bounding box with invisible regions"}. This record does not assert independent reproduction.

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