# BEV Segmentation on V2X-Sim 1.0 (test)

Source: [BEV Segmentation on V2X-Sim 1.0 (test)](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test>)

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

Data updated: 2026-02-26T06:08:12.269Z

Evaluation of Bird's Eye View (BEV) semantic segmentation performance on the test split of the V2X-Sim 1.0 dataset, reporting class-specific IoU scores for categories like Vehicle, Road, and Sidewalk.

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 | BEV segmentation |
| Dataset (including any stated split) | V2X-Sim 1.0 (test) |
| Metric | Vehicle IoU |
| 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

- [Vehicle IoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=Vehicle%20IoU>): Higher is better; unit: PERCENT.

- [Sidewalk IoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=Sidewalk%20IoU>): Higher is better; unit: PERCENT.

- [Terrain IoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=Terrain%20IoU>): Higher is better; unit: PERCENT.

- [Road IoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=Road%20IoU>): Higher is better; unit: PERCENT.

- [Buildings IoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=Buildings%20IoU>): Higher is better; unit: PERCENT.

- [Pedestrian IoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=Pedestrian%20IoU>): Higher is better; unit: PERCENT.

- [Vegetation IoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=Vegetation%20IoU>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/bev-segmentation-on-v2x-sim-1-0-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Vehicle IoU | Result date | Report paper |
| --- | --- | --- | --- |
| Upper-bound | 55.58 | Not recorded | 68fa7a2d1e209131cea81912 |
| CP-uniGuard | 52.84 | Not recorded | 68fa7a2d1e209131cea81912 |
| CP-uniGuard | 52.76 | Not recorded | 68fa7a2d1e209131cea81912 |
| CP-uniGuard | 49.22 | Not recorded | 68fa7a2d1e209131cea81912 |
| Lower-bound | 47.06 | Not recorded | 68fa7a2d1e209131cea81912 |
| No Defense | 34.53 | Not recorded | 68fa7a2d1e209131cea81912 |
| No Defense | 26.8 | Not recorded | 68fa7a2d1e209131cea81912 |
| No Defense | 22.5 | Not recorded | 68fa7a2d1e209131cea81912 |

### Upper-bound

Vehicle IoU: 55.58. Result ID: 699a485d5698665ec4cfb8fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Perception Protocol":"Collaborative","Attack Scenario":"None (All benign agents)"}. This record does not assert independent reproduction.

### CP-uniGuard

Vehicle IoU: 52.84. Result ID: 699a485d5698665ec4cfb8ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Attack Scenario":"PGD attack","Perception Protocol":"Collaborative"}. This record does not assert independent reproduction.

### CP-uniGuard

Vehicle IoU: 52.76. Result ID: 699a485d5698665ec4cfb8fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Attack Scenario":"FGSM attack","Perception Protocol":"Collaborative"}. This record does not assert independent reproduction.

### CP-uniGuard

Vehicle IoU: 49.22. Result ID: 699a485d5698665ec4cfb8fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Attack Scenario":"C&W attack","Perception Protocol":"Collaborative"}. This record does not assert independent reproduction.

### Lower-bound

Vehicle IoU: 47.06. Result ID: 699a485d5698665ec4cfb900.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Perception Protocol":"Individual perception","Attack Scenario":"None"}. This record does not assert independent reproduction.

### No Defense

Vehicle IoU: 34.53. Result ID: 699a485d5698665ec4cfb902.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Attack Scenario":"C&W attack","Fusion Method":"V2VNet"}. This record does not assert independent reproduction.

### No Defense

Vehicle IoU: 26.8. Result ID: 699a485d5698665ec4cfb901.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Attack Scenario":"FGSM attack","Fusion Method":"V2VNet"}. This record does not assert independent reproduction.

### No Defense

Vehicle IoU: 22.5. Result ID: 699a485d5698665ec4cfb903.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Attack Scenario":"PGD attack","Fusion Method":"V2VNet"}. This record does not assert independent reproduction.

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