# Semantic Occupancy Forecasting on SemanticKITTI (val)

Source: [Semantic Occupancy Forecasting on SemanticKITTI (val)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val>)

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

Data updated: 2026-02-26T06:10:53.670Z

Evaluation of Semantic Occupancy Forecasting performance on the validation split of the SemanticKITTI dataset, reporting IoU and mIoU metrics across various forecast horizons (1s, 2s, 3s).

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 | Semantic Occupancy Forecasting |
| Dataset (including any stated split) | SemanticKITTI (val) |
| Metric | mIoU (1s) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [mIoU (1s)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=mIoU%20(1s)>): Higher is better; unit: PERCENT.

- [mIoU (2s)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=mIoU%20(2s)>): Higher is better; unit: PERCENT.

- [mIoU (3s)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=mIoU%20(3s)>): Higher is better; unit: PERCENT.

- [mIoU (Avg)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=mIoU%20(Avg)>): Higher is better; unit: PERCENT.

- [IoU (1s)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=IoU%20(1s)>): Higher is better; unit: PERCENT.

- [IoU (2s)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=IoU%20(2s)>): Higher is better; unit: PERCENT.

- [IoU (3s)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=IoU%20(3s)>): Higher is better; unit: PERCENT.

- [IoU (Avg)](<https://www.sota2.com/research/sota/semantic-occupancy-forecasting-on-semantickitti-val.md?metric=IoU%20(Avg)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU (1s) | Result date | Report paper |
| --- | --- | --- | --- |
| ForecastOcc-COTR | 9.89 | Not recorded | 698abbc0c97a0b3e3b5de0ed |
| ForecastOcc | 9.1 | Not recorded | 698abbc0c97a0b3e3b5de0ed |
| PDCast | 7.48 | Not recorded | 698abbc0c97a0b3e3b5de0ed |
| Naive | 5.32 | Not recorded | 698abbc0c97a0b3e3b5de0ed |

### ForecastOcc-COTR

mIoU (1s): 9.89. Result ID: 69972a615698665ec4793b10.

[Reporting paper](<https://www.sota2.com/research/paper/698abbc0c97a0b3e3b5de0ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abbc0c97a0b3e3b5de0ed.md>)

Recorded evaluation configuration: {"input":"monocular camera images","backbone":"COTR"}. This record does not assert independent reproduction.

### ForecastOcc

mIoU (1s): 9.1. Result ID: 69972a615698665ec4793b0f.

[Reporting paper](<https://www.sota2.com/research/paper/698abbc0c97a0b3e3b5de0ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abbc0c97a0b3e3b5de0ed.md>)

Recorded evaluation configuration: {"input":"monocular camera images"}. This record does not assert independent reproduction.

### PDCast

mIoU (1s): 7.48. Result ID: 69972a615698665ec4793b0e.

[Reporting paper](<https://www.sota2.com/research/paper/698abbc0c97a0b3e3b5de0ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74d81e209131cea6417d.md>)

Recorded evaluation configuration: {"input":"monocular camera images"}. This record does not assert independent reproduction.

### Naive

mIoU (1s): 5.32. Result ID: 69972a615698665ec4793b0d.

[Reporting paper](<https://www.sota2.com/research/paper/698abbc0c97a0b3e3b5de0ed.md>)

Recorded evaluation configuration: {"input":"monocular camera images"}. This record does not assert independent reproduction.

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