# 3D Object Detection on VoD Target RaCFormer base

Source: [3D Object Detection on VoD Target RaCFormer base](<https://www.sota2.com/research/sota/3d-object-detection-on-vod-target-racformer-base>)

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

Data updated: 2026-06-11T10:06:23.770Z

Evaluation of 3D Object Detection performance on the View-of-Delft (VoD) dataset using the specific 'Target RaCFormer base' configuration, reporting class-specific metrics for Car, Pedestrian, and Cyclist, along with overall mAP.

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) | VoD Target RaCFormer base |
| Metric | Car AP |
| 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

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

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

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

- [mAP](<https://www.sota2.com/research/sota/3d-object-detection-on-vod-target-racformer-base.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Car AP | Result date | Report paper |
| --- | --- | --- | --- |
| Oracle | 47.3 | Not recorded | 6a2a4130d33dfb23e78393d0 |
| VBS2M | 36.08 | Not recorded | 6a2a4130d33dfb23e78393d0 |
| Source Only | 29.31 | Not recorded | 6a2a4130d33dfb23e78393d0 |
| SPG | 28.96 | Not recorded | 6a2a4130d33dfb23e78393d0 |
| CPerb | 28.42 | Not recorded | 6a2a4130d33dfb23e78393d0 |
| DG-GCD | 27.85 | Not recorded | 6a2a4130d33dfb23e78393d0 |
| VL2V-ADiP | 26.5 | Not recorded | 6a2a4130d33dfb23e78393d0 |

### Oracle

Car AP: 47.3. Result ID: 6a2a8842fbc373592c283b80.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

Recorded evaluation configuration: {"Backbone":"RaCFormer"}. This record does not assert independent reproduction.

### VBS2M

Car AP: 36.08. Result ID: 6a2a8842fbc373592c283b86.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

Recorded evaluation configuration: {"Backbone":"RaCFormer"}. This record does not assert independent reproduction.

### Source Only

Car AP: 29.31. Result ID: 6a2a8842fbc373592c283b81.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

Recorded evaluation configuration: {"Backbone":"RaCFormer"}. This record does not assert independent reproduction.

### SPG

Car AP: 28.96. Result ID: 6a2a8842fbc373592c283b84.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a8b1e209131cea28a9a.md>)

Recorded evaluation configuration: {"Backbone":"RaCFormer"}. This record does not assert independent reproduction.

### CPerb

Car AP: 28.42. Result ID: 6a2a8842fbc373592c283b83.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738e1e209131cea5d33f.md>)

Recorded evaluation configuration: {"Backbone":"RaCFormer"}. This record does not assert independent reproduction.

### DG-GCD

Car AP: 27.85. Result ID: 6a2a8842fbc373592c283b82.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77941e209131cea741c5.md>)

Recorded evaluation configuration: {"Backbone":"RaCFormer"}. This record does not assert independent reproduction.

### VL2V-ADiP

Car AP: 26.5. Result ID: 6a2a8842fbc373592c283b85.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4130d33dfb23e78393d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea565a1.md>)

[Implementation](<https://github.com/val-iisc/VL2V-ADiP.git>)

Recorded evaluation configuration: {"Backbone":"RaCFormer"}. This record does not assert independent reproduction.

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