# Semantic 3D Reconstruction on Mip-NeRF 360 (Efficiency Metrics)

Source: [Semantic 3D Reconstruction on Mip-NeRF 360 (Efficiency Metrics)](<https://www.sota2.com/research/sota/semantic-3d-reconstruction-on-mip-nerf-360-efficiency-metrics>)

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

Data updated: 2026-05-14T09:45:59.656Z

Evaluation of Semantic 3D Reconstruction performance on the Mip-NeRF 360 dataset, focusing on reconstruction time (2D to 3D), peak GPU memory usage, and rendering speed (3D to 2D).

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 3D Reconstruction |
| Dataset (including any stated split) | Mip-NeRF 360 |
| Metric | Reconstruction Time (2D to 3D) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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

- [Reconstruction Time (2D to 3D)](<https://www.sota2.com/research/sota/semantic-3d-reconstruction-on-mip-nerf-360-efficiency-metrics.md?metric=Reconstruction%20Time%20(2D%20to%203D)>): Lower is better; unit: TIME.

- [GPU Memory (GB)](<https://www.sota2.com/research/sota/semantic-3d-reconstruction-on-mip-nerf-360-efficiency-metrics.md?metric=GPU%20Memory%20(GB)>): Lower is better; unit: SIZE.

- [Rendering Speed (FPS)](<https://www.sota2.com/research/sota/semantic-3d-reconstruction-on-mip-nerf-360-efficiency-metrics.md?metric=Rendering%20Speed%20(FPS)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Reconstruction Time (2D to 3D) | Result date | Report paper |
| --- | --- | --- | --- |
| SCOUP | 1.4 | Not recorded | 6a055726dbc836b87d828d62 |
| LangSplatV2 | 684 | Not recorded | 6a055726dbc836b87d828d62 |

### SCOUP

Reconstruction Time (2D to 3D): 1.4. Result ID: 6a0598dc47f34ce924ed052c.

[Reporting paper](<https://www.sota2.com/research/paper/6a055726dbc836b87d828d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a055726dbc836b87d828d62.md>)

Recorded evaluation configuration: {"Hardware":"NVIDIA RTX A6000"}. This record does not assert independent reproduction.

### LangSplatV2

Reconstruction Time (2D to 3D): 684. Result ID: 6a0598dc47f34ce924ed052b.

[Reporting paper](<https://www.sota2.com/research/paper/6a055726dbc836b87d828d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1d1e209131cea8c780.md>)

Recorded evaluation configuration: {"Hardware":"NVIDIA RTX A6000"}. This record does not assert independent reproduction.

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