# 4D Panoptic Segmentation on SemanticKITTI 1.0 (test)

Source: [4D Panoptic Segmentation on SemanticKITTI 1.0 (test)](<https://www.sota2.com/research/sota/4d-panoptic-segmentation-on-semantickitti-1-0-test>)

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

Data updated: 2026-02-26T05:48:21.600Z

Evaluation of 4D Panoptic Segmentation performance on the test split of the SemanticKITTI 1.0 dataset, reporting metrics including LSTQ, Sassoc, Scls, IoUSt, and IoUTh.

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 | 4D Panoptic Segmentation |
| Dataset (including any stated split) | SemanticKITTI 1.0 (test) |
| Metric | LSTQ |
| 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

- [LSTQ](<https://www.sota2.com/research/sota/4d-panoptic-segmentation-on-semantickitti-1-0-test.md?metric=LSTQ>): Higher is better; unit: PERCENT.

- [Sassoc](<https://www.sota2.com/research/sota/4d-panoptic-segmentation-on-semantickitti-1-0-test.md?metric=Sassoc>): Higher is better; unit: PERCENT.

- [Scls](<https://www.sota2.com/research/sota/4d-panoptic-segmentation-on-semantickitti-1-0-test.md?metric=Scls>): Higher is better; unit: PERCENT.

- [IoUSt](<https://www.sota2.com/research/sota/4d-panoptic-segmentation-on-semantickitti-1-0-test.md?metric=IoUSt>): Higher is better; unit: PERCENT.

- [IoUTh](<https://www.sota2.com/research/sota/4d-panoptic-segmentation-on-semantickitti-1-0-test.md?metric=IoUTh>): Higher is better; unit: PERCENT.

## Recorded results

| Method | LSTQ | Result date | Report paper |
| --- | --- | --- | --- |
| 4D-PLS | 56.89 | Not recorded | 68fa69ae1e209131cea23576 |
| 4D-PLS | 43.88 | Not recorded | 68fa69ae1e209131cea23576 |
| 4D-PLS | 40.18 | Not recorded | 68fa69ae1e209131cea23576 |
| KPConv | 38.53 | Not recorded | 68fa69ae1e209131cea23576 |
| KPConv | 38.01 | Not recorded | 68fa69ae1e209131cea23576 |
| RangeNet++ | 35.52 | Not recorded | 68fa69ae1e209131cea23576 |
| RangeNet++ | 34.91 | Not recorded | 68fa69ae1e209131cea23576 |

### 4D-PLS

LSTQ: 56.89. Result ID: 698dd0c88b517eb43323eb5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Implementation](<https://github.com/mehmetaygun/4d-pls>)

Recorded evaluation configuration: {"scan\_mode":"multi scan"}. This record does not assert independent reproduction.

### 4D-PLS

LSTQ: 43.88. Result ID: 698dd0c88b517eb43323eb59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Implementation](<https://github.com/mehmetaygun/4d-pls>)

Recorded evaluation configuration: {"scan\_mode":"single scan","tracker":"SFP \[49\]"}. This record does not assert independent reproduction.

### 4D-PLS

LSTQ: 40.18. Result ID: 698dd0c88b517eb43323eb58.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Implementation](<https://github.com/mehmetaygun/4d-pls>)

Recorded evaluation configuration: {"scan\_mode":"single scan","tracker":"MOT \[76\]"}. This record does not assert independent reproduction.

### KPConv

LSTQ: 38.53. Result ID: 698dd0c88b517eb43323eb57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66341e209131cea0ebe7.md>)

[Implementation](<https://github.com/HuguesTHOMAS/KPConv>)

Recorded evaluation configuration: {"detector":"PointPillars \[40\]","tracker":"SFP \[49\]"}. This record does not assert independent reproduction.

### KPConv

LSTQ: 38.01. Result ID: 698dd0c88b517eb43323eb55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66341e209131cea0ebe7.md>)

[Implementation](<https://github.com/HuguesTHOMAS/KPConv>)

Recorded evaluation configuration: {"detector":"PointPillars \[40\]","tracker":"MOT \[76\]"}. This record does not assert independent reproduction.

### RangeNet++

LSTQ: 35.52. Result ID: 698dd0c88b517eb43323eb54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

Recorded evaluation configuration: {"detector":"PointPillars \[40\]","tracker":"MOT \[76\]"}. This record does not assert independent reproduction.

### RangeNet++

LSTQ: 34.91. Result ID: 698dd0c88b517eb43323eb56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea23576.md>)

Recorded evaluation configuration: {"detector":"PointPillars \[40\]","tracker":"SFP \[49\]"}. This record does not assert independent reproduction.

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