# Scene-level Reconstruction on Synthetic Room Dataset 3K sparse input points

Source: [Scene-level Reconstruction on Synthetic Room Dataset 3K sparse input points](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-room-dataset-3k-sparse-input-points>)

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

Data updated: 2026-02-26T05:47:20.032Z

Evaluation of models performing scene-level 3D reconstruction using the Synthetic Room Dataset (3K sparse input points), measured by IoU, Chamfer-L1 distance, Normal Consistency (NC), and F-score.

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 | Scene-level Reconstruction |
| Dataset (including any stated split) | Synthetic Room Dataset 3K sparse input points |
| Metric | IoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [IoU](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-room-dataset-3k-sparse-input-points.md?metric=IoU>): Higher is better; unit: PERCENT.

- [Chamfer-L1 Distance](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-room-dataset-3k-sparse-input-points.md?metric=Chamfer-L1%20Distance>): Lower is better; unit: SCALAR.

- [NC](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-room-dataset-3k-sparse-input-points.md?metric=NC>): Higher is better; unit: PERCENT.

- [F-score](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-room-dataset-3k-sparse-input-points.md?metric=F-score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | IoU | Result date | Report paper |
| --- | --- | --- | --- |
| ALTO | 88.2 | Not recorded | 68fa6e2b1e209131cea3e4d6 |
| ConvONet | 81.8 | Not recorded | 68fa6e2b1e209131cea3e4d6 |
| POCO | 80.1 | Not recorded | 68fa6e2b1e209131cea3e4d6 |

### ALTO

IoU: 88.2. Result ID: 6990133b3a6c314849fdf206.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2b1e209131cea3e4d6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2b1e209131cea3e4d6.md>)

[Implementation](<https://visual.ee.ucla.edu/alto.htm/>)

Recorded evaluation configuration: {"Number of input points":"3K"}. This record does not assert independent reproduction.

### ConvONet

IoU: 81.8. Result ID: 6990133b3a6c314849fdf204.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2b1e209131cea3e4d6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68131e209131cea1a017.md>)

Recorded evaluation configuration: {"Number of input points":"3K"}. This record does not assert independent reproduction.

### POCO

IoU: 80.1. Result ID: 6990133b3a6c314849fdf205.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2b1e209131cea3e4d6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c181e209131cea321d0.md>)

[Implementation](<https://github.com/valeoai/POCO>)

Recorded evaluation configuration: {"Number of input points":"3K"}. This record does not assert independent reproduction.

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