# Cuboid Autolabeling on KITTI Moderate

Source: [Cuboid Autolabeling on KITTI Moderate](<https://www.sota2.com/research/sota/cuboid-autolabeling-on-kitti-moderate>)

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

Data updated: 2026-02-26T05:36:43.933Z

Evaluation of Cuboid Autolabeling performance on the Moderate subset of the KITTI dataset, reporting metrics such as BEV, 3D accuracy, and Novelty Score (NS) at various IoU thresholds.

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 | Cuboid Autolabeling |
| Dataset (including any stated split) | KITTI Moderate |
| Metric | BEV@0.5 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [BEV@0.5](<https://www.sota2.com/research/sota/cuboid-autolabeling-on-kitti-moderate.md?metric=BEV%400.5>): Higher is better; unit: PERCENT.

- [3D@0.5](<https://www.sota2.com/research/sota/cuboid-autolabeling-on-kitti-moderate.md?metric=3D%400.5>): Higher is better; unit: PERCENT.

- [NS@0.5](<https://www.sota2.com/research/sota/cuboid-autolabeling-on-kitti-moderate.md?metric=NS%400.5>): Higher is better; unit: PERCENT.

- [NS@1.0](<https://www.sota2.com/research/sota/cuboid-autolabeling-on-kitti-moderate.md?metric=NS%401.0>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BEV@0.5 | Result date | Report paper |
| --- | --- | --- | --- |
| CSS Net | 63.36 | Not recorded | 68fa67561e209131cea159c9 |
| 3D Autolabeling Pipeline (CSS Net) | 63.36 | Not recorded | 68fa67561e209131cea159c9 |
| CSS Net | 61.17 | Not recorded | 68fa67561e209131cea159c9 |
| 3D Autolabeling Pipeline (CSS Net) | 61.17 | Not recorded | 68fa67561e209131cea159c9 |
| CSS Net | 59.75 | Not recorded | 68fa67561e209131cea159c9 |
| 3D Autolabeling Pipeline (CSS Net) | 59.75 | Not recorded | 68fa67561e209131cea159c9 |

### CSS Net

BEV@0.5: 63.36. Result ID: 698d2d938b517eb4331f934b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Implementation](<http://github.com/TRI-ML/sdflabel>)

Recorded evaluation configuration: {"Loop":"2","Input Source":"MASK-RCNN"}. This record does not assert independent reproduction.

### 3D Autolabeling Pipeline (CSS Net)

BEV@0.5: 63.36. Result ID: 698d2d938b517eb4331f9367.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Implementation](<http://github.com/TRI-ML/sdflabel>)

Recorded evaluation configuration: {"Loop":"2","Input Source":"Mask-RCNN"}. This record does not assert independent reproduction.

### CSS Net

BEV@0.5: 61.17. Result ID: 698d2d938b517eb4331f934a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Implementation](<http://github.com/TRI-ML/sdflabel>)

Recorded evaluation configuration: {"Loop":"2","Input Source":"RCNN"}. This record does not assert independent reproduction.

### 3D Autolabeling Pipeline (CSS Net)

BEV@0.5: 61.17. Result ID: 698d2d938b517eb4331f9366.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Implementation](<http://github.com/TRI-ML/sdflabel>)

Recorded evaluation configuration: {"Loop":"2","Input Source":"RCNN"}. This record does not assert independent reproduction.

### CSS Net

BEV@0.5: 59.75. Result ID: 698d2d938b517eb4331f9349.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Implementation](<http://github.com/TRI-ML/sdflabel>)

Recorded evaluation configuration: {"Loop":"2","Input Source":"KITTI GT"}. This record does not assert independent reproduction.

### 3D Autolabeling Pipeline (CSS Net)

BEV@0.5: 59.75. Result ID: 698d2d938b517eb4331f9365.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c9.md>)

[Implementation](<http://github.com/TRI-ML/sdflabel>)

Recorded evaluation configuration: {"Loop":"2","Input Source":"KITTI GT"}. This record does not assert independent reproduction.

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