# 3D Object Detection on V2XSet Noisy setting

Source: [3D Object Detection on V2XSet Noisy setting](<https://www.sota2.com/research/sota/3d-object-detection-on-v2xset-noisy-setting>)

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

Data updated: 2026-02-26T05:23:22.875Z

Evaluation of 3D Object Detection performance on the V2XSet dataset specifically under the Noisy setting, reporting AP metrics at IoU thresholds of 0.5 and 0.7.

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) | V2XSet Noisy setting |
| Metric | AP@0.5 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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@0.5](<https://www.sota2.com/research/sota/3d-object-detection-on-v2xset-noisy-setting.md?metric=AP%400.5>): Higher is better; unit: PERCENT.

- [AP@0.7](<https://www.sota2.com/research/sota/3d-object-detection-on-v2xset-noisy-setting.md?metric=AP%400.7>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP@0.5 | Result date | Report paper |
| --- | --- | --- | --- |
| V2X-ViT | 83.6 | Not recorded | 68fa6d351e209131cea386f5 |
| DiscoNet | 79.8 | Not recorded | 68fa6d351e209131cea386f5 |
| V2VNet | 79.1 | Not recorded | 68fa6d351e209131cea386f5 |
| Early Fusion | 72 | Not recorded | 68fa6d351e209131cea386f5 |
| F-Cooper | 71.5 | Not recorded | 68fa6d351e209131cea386f5 |
| OPV2V | 70.9 | Not recorded | 68fa6d351e209131cea386f5 |
| No Fusion | 60.6 | Not recorded | 68fa6d351e209131cea386f5 |
| Late Fusion | 54.9 | Not recorded | 68fa6d351e209131cea386f5 |

### V2X-ViT

AP@0.5: 83.6. Result ID: 698f83ed3a6c314849f99170.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

[Implementation](<https://github.com/DerrickXuNu/v2x-vit>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m","Compression rate":"32","Fusion strategy":"Intermediate","Fine-tuned":true,"Encoder layers":3,"MSwin window sizes":"4, 8, 16"}. This record does not assert independent reproduction.

### DiscoNet

AP@0.5: 79.8. Result ID: 698f83ed3a6c314849f9916f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b971e209131cea2f17f.md>)

[Implementation](<https://github.com/ai4ce/DiscoNet>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m","Compression rate":"32","Fusion strategy":"Intermediate"}. This record does not assert independent reproduction.

### V2VNet

AP@0.5: 79.1. Result ID: 698f83ed3a6c314849f9916e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68281e209131cea1a5bb.md>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m","Compression rate":"32","Fusion strategy":"Intermediate"}. This record does not assert independent reproduction.

### Early Fusion

AP@0.5: 72. Result ID: 698f83ed3a6c314849f9916b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0bff4.md>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m"}. This record does not assert independent reproduction.

### F-Cooper

AP@0.5: 71.5. Result ID: 698f83ed3a6c314849f9916c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66641e209131cea100c7.md>)

[Implementation](<https://www.acm.org/publications/proceedings-template>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m","Compression rate":"32","Fusion strategy":"Intermediate"}. This record does not assert independent reproduction.

### OPV2V

AP@0.5: 70.9. Result ID: 698f83ed3a6c314849f9916d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd91e209131cea363e4.md>)

[Implementation](<https://mobility-lab.seas.ucla.edu/opv2v/>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m","Compression rate":"32","Fusion strategy":"Intermediate"}. This record does not assert independent reproduction.

### No Fusion

AP@0.5: 60.6. Result ID: 698f83ed3a6c314849f99169.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m"}. This record does not assert independent reproduction.

### Late Fusion

AP@0.5: 54.9. Result ID: 698f83ed3a6c314849f9916a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386f5.md>)

Recorded evaluation configuration: {"Backbone":"PointPillar","Voxel resolution":"0.4 m"}. This record does not assert independent reproduction.

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