# Surface Reconstruction on Synthetic Rooms 10k noisy points (test)

Source: [Surface Reconstruction on Synthetic Rooms 10k noisy points (test)](<https://www.sota2.com/research/sota/surface-reconstruction-on-synthetic-rooms-10k-noisy-points-test>)

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

Data updated: 2026-02-26T05:39:03.445Z

Evaluation of 3D Surface Reconstruction performance on the Synthetic Rooms 10k noisy points test set, reporting metrics such as IoU, Chamfer Distance (CD), Normal Consistency (NC), and F-Score (FS).

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 | Surface Reconstruction |
| Dataset (including any stated split) | Synthetic Rooms 10k noisy points (test) |
| Metric | Chamfer Distance (CD) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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

- [Chamfer Distance (CD)](<https://www.sota2.com/research/sota/surface-reconstruction-on-synthetic-rooms-10k-noisy-points-test.md?metric=Chamfer%20Distance%20(CD)>): Lower is better; unit: SCALAR.

- [IoU](<https://www.sota2.com/research/sota/surface-reconstruction-on-synthetic-rooms-10k-noisy-points-test.md?metric=IoU>): Higher is better; unit: PERCENT.

- [Normal Consistency (NC)](<https://www.sota2.com/research/sota/surface-reconstruction-on-synthetic-rooms-10k-noisy-points-test.md?metric=Normal%20Consistency%20(NC)>): Higher is better; unit: PERCENT.

- [F-Score (FS)](<https://www.sota2.com/research/sota/surface-reconstruction-on-synthetic-rooms-10k-noisy-points-test.md?metric=F-Score%20(FS)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Chamfer Distance (CD) | Result date | Report paper |
| --- | --- | --- | --- |
| POCO | 0.36 | Not recorded | 68fa6c181e209131cea321d0 |
| ConvONet | 0.42 | Not recorded | 68fa6c181e209131cea321d0 |
| DP-ConvONet | 0.42 | Not recorded | 68fa6c181e209131cea321d0 |
| SPR trimmed | 0.69 | Not recorded | 68fa6c181e209131cea321d0 |
| ONet | 2.03 | Not recorded | 68fa6c181e209131cea321d0 |
| SPR | 2.23 | Not recorded | 68fa6c181e209131cea321d0 |

### POCO

Chamfer Distance (CD): 0.36. Result ID: 698ecfdcffc3901de0a18880.

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

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

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

Recorded evaluation configuration: {"uses normals":false}. This record does not assert independent reproduction.

### ConvONet

Chamfer Distance (CD): 0.42. Result ID: 698ecfdcffc3901de0a1887e.

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

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

Recorded evaluation configuration: {"uses normals":false}. This record does not assert independent reproduction.

### DP-ConvONet

Chamfer Distance (CD): 0.42. Result ID: 698ecfdcffc3901de0a1887f.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"uses normals":false}. This record does not assert independent reproduction.

### SPR trimmed

Chamfer Distance (CD): 0.69. Result ID: 698ecfdcffc3901de0a1887d.

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

Recorded evaluation configuration: {"uses normals":true}. This record does not assert independent reproduction.

### ONet

Chamfer Distance (CD): 2.03. Result ID: 698ecfdcffc3901de0a1887b.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a71e209131cea0ba34.md>)

Recorded evaluation configuration: {"uses normals":false}. This record does not assert independent reproduction.

### SPR

Chamfer Distance (CD): 2.23. Result ID: 698ecfdcffc3901de0a1887c.

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

Recorded evaluation configuration: {"uses normals":true}. This record does not assert independent reproduction.

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