# 3D Object Detection on Omni3D Full Unified (test)

Source: [3D Object Detection on Omni3D Full Unified (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test>)

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

Data updated: 2026-02-26T05:23:11.061Z

Evaluation of 3D Object Detection performance on the test split of the Omni3D Full Unified dataset, reporting AP metrics across various categories.

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) | Omni3D Full Unified (test) |
| Metric | AP 3D (Overall) |
| 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

- [AP 3D (Overall)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test.md?metric=AP%203D%20(Overall)>): Higher is better; unit: PERCENT.

- [AP 3D (KITTI)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test.md?metric=AP%203D%20(KITTI)>): Higher is better; unit: PERCENT.

- [AP 3D (NuScenes)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test.md?metric=AP%203D%20(NuScenes)>): Higher is better; unit: PERCENT.

- [AP 3D (SUN RGB-D)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test.md?metric=AP%203D%20(SUN%20RGB-D)>): Higher is better; unit: PERCENT.

- [AP 3D (Argoverse)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test.md?metric=AP%203D%20(Argoverse)>): Higher is better; unit: PERCENT.

- [AP 3D (ObjectNet)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test.md?metric=AP%203D%20(ObjectNet)>): Higher is better; unit: PERCENT.

- [AP 3D (Hype)](<https://www.sota2.com/research/sota/3d-object-detection-on-omni3d-full-unified-test.md?metric=AP%203D%20(Hype)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP 3D (Overall) | Result date | Report paper |
| --- | --- | --- | --- |
| LocateAnything3D | 38.9 | Not recorded | 692689c7d6b0dd3342930655 |
| DetAny3D | 34.38 | Not recorded | 692689c7d6b0dd3342930655 |
| DetAny3D | 24.92 | Not recorded | 692689c7d6b0dd3342930655 |
| Cube R-CNN | 23.26 | Not recorded | 692689c7d6b0dd3342930655 |
| OVMono3D | 22.98 | Not recorded | 692689c7d6b0dd3342930655 |
| SMOKE | 10.4 | Not recorded | 692689c7d6b0dd3342930655 |
| ImVoxelNet | 9.4 | Not recorded | 692689c7d6b0dd3342930655 |

### LocateAnything3D

AP 3D (Overall): 38.9. Result ID: 699d4e055698665ec4f055be.

[Reporting paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.md>)

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

### DetAny3D

AP 3D (Overall): 34.38. Result ID: 699d4e055698665ec4f055bd.

[Reporting paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793e1e209131cea7cd17.md>)

Recorded evaluation configuration: {"input":"Ground-Truth 2D Box"}. This record does not assert independent reproduction.

### DetAny3D

AP 3D (Overall): 24.92. Result ID: 699d4e055698665ec4f055bc.

[Reporting paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793e1e209131cea7cd17.md>)

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

### Cube R-CNN

AP 3D (Overall): 23.26. Result ID: 699d4e055698665ec4f055ba.

[Reporting paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.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.

### OVMono3D

AP 3D (Overall): 22.98. Result ID: 699d4e055698665ec4f055bb.

[Reporting paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e31e209131cea6a768.md>)

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

### SMOKE

AP 3D (Overall): 10.4. Result ID: 699d4e055698665ec4f055b9.

[Reporting paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67181e209131cea1418c.md>)

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

### ImVoxelNet

AP 3D (Overall): 9.4. Result ID: 699d4e055698665ec4f055b8.

[Reporting paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930655.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.

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