# Urban Scene Reconstruction on PandaSet Extrapolation Moderate (test)

Source: [Urban Scene Reconstruction on PandaSet Extrapolation Moderate (test)](<https://www.sota2.com/research/sota/urban-scene-reconstruction-on-pandaset-extrapolation-moderate-test>)

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

Data updated: 2026-05-22T08:56:35.237Z

Evaluation of Urban Scene Reconstruction performance on the moderate extrapolation split of the PandaSet dataset, measured using image fidelity metrics (FID@1m, FID@2m, FID@3m) and reconstruction time.

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 | Urban Scene Reconstruction |
| Dataset (including any stated split) | PandaSet Extrapolation Moderate (test) |
| Metric | FID@1m |
| Unit | SCALAR |
| Direction | Lower 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

- [FID@1m](<https://www.sota2.com/research/sota/urban-scene-reconstruction-on-pandaset-extrapolation-moderate-test.md?metric=FID%401m>): Lower is better; unit: SCALAR.

- [FID@2m](<https://www.sota2.com/research/sota/urban-scene-reconstruction-on-pandaset-extrapolation-moderate-test.md?metric=FID%402m>): Lower is better; unit: SCALAR.

- [FID@3m](<https://www.sota2.com/research/sota/urban-scene-reconstruction-on-pandaset-extrapolation-moderate-test.md?metric=FID%403m>): Lower is better; unit: SCALAR.

- [Reconstruction Time](<https://www.sota2.com/research/sota/urban-scene-reconstruction-on-pandaset-extrapolation-moderate-test.md?metric=Reconstruction%20Time>): Lower is better; unit: TIME.

## Recorded results

| Method | FID@1m | Result date | Report paper |
| --- | --- | --- | --- |
| StreetCrafter | 59.44 | Not recorded | 6a0fe30af984739ed6739d63 |
| Difix3D | 60.29 | Not recorded | 6a0fe30af984739ed6739d63 |
| GenRe+ | 60.69 | Not recorded | 6a0fe30af984739ed6739d63 |
| StreetGS | 68.99 | Not recorded | 6a0fe30af984739ed6739d63 |
| GNet | 70.04 | Not recorded | 6a0fe30af984739ed6739d63 |
| 3DGS | 82.63 | Not recorded | 6a0fe30af984739ed6739d63 |
| SplatAD | 84.21 | Not recorded | 6a0fe30af984739ed6739d63 |
| G3R | 89.75 | Not recorded | 6a0fe30af984739ed6739d63 |

### StreetCrafter

FID@1m: 59.44. Result ID: 6a101a2bfbc373592c093e65.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae41e209131cea85b8c.md>)

[Implementation](<https://zju3dv.github.io/street_crafter>)

Recorded evaluation configuration: {"Setting":"Reconstruction with neural fixers"}. This record does not assert independent reproduction.

### Difix3D

FID@1m: 60.29. Result ID: 6a101a2bfbc373592c093e66.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77381e209131cea71c37.md>)

Recorded evaluation configuration: {"Setting":"Reconstruction with neural fixers"}. This record does not assert independent reproduction.

### GenRe+

FID@1m: 60.69. Result ID: 6a101a2bfbc373592c093e67.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

Recorded evaluation configuration: {"Setting":"Reconstruction with neural fixers"}. This record does not assert independent reproduction.

### StreetGS

FID@1m: 68.99. Result ID: 6a101a2bfbc373592c093e61.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74891e209131cea624fa.md>)

Recorded evaluation configuration: {"Setting":"Standalone reconstruction"}. This record does not assert independent reproduction.

### GNet

FID@1m: 70.04. Result ID: 6a101a2bfbc373592c093e64.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

Recorded evaluation configuration: {"Setting":"Standalone reconstruction"}. This record does not assert independent reproduction.

### 3DGS

FID@1m: 82.63. Result ID: 6a101a2bfbc373592c093e60.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70461e209131cea4a191.md>)

[Implementation](<https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/>)

Recorded evaluation configuration: {"Setting":"Standalone reconstruction"}. This record does not assert independent reproduction.

### SplatAD

FID@1m: 84.21. Result ID: 6a101a2bfbc373592c093e62.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa776a1e209131cea73228.md>)

Recorded evaluation configuration: {"Setting":"Standalone reconstruction"}. This record does not assert independent reproduction.

### G3R

FID@1m: 89.75. Result ID: 6a101a2bfbc373592c093e63.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30af984739ed6739d63.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea654cb.md>)

Recorded evaluation configuration: {"Setting":"Standalone reconstruction"}. This record does not assert independent reproduction.

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