# Point Cloud Mosaicking on 3RScan (143 scenes)

Source: [Point Cloud Mosaicking on 3RScan (143 scenes)](<https://www.sota2.com/research/sota/point-cloud-mosaicking-on-3rscan-143-scenes>)

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

Data updated: 2026-02-26T05:29:30.852Z

Evaluation of Point Cloud Mosaicking performance on the 143-scene subset of the 3RScan dataset, reporting Accuracy, Completeness, Precision, Recall, and F1-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 | Point cloud mosaicking |
| Dataset (including any stated split) | 3RScan (143 scenes) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/point-cloud-mosaicking-on-3rscan-143-scenes.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Completeness](<https://www.sota2.com/research/sota/point-cloud-mosaicking-on-3rscan-143-scenes.md?metric=Completeness>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/point-cloud-mosaicking-on-3rscan-143-scenes.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/point-cloud-mosaicking-on-3rscan-143-scenes.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1-Score](<https://www.sota2.com/research/sota/point-cloud-mosaicking-on-3rscan-143-scenes.md?metric=F1-Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GeoTr | 12.13 | Not recorded | 68fa72ae1e209131cea57d30 |
| SGA | 0.94 | Not recorded | 68fa72ae1e209131cea57d30 |
| SG-PGM | 0.33 | Not recorded | 68fa72ae1e209131cea57d30 |
| SGPGM+R | 0.24 | Not recorded | 68fa72ae1e209131cea57d30 |

### GeoTr

Accuracy: 12.13. Result ID: 69924ebd3a6c3148490e0f2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48df8.md>)

[Implementation](<https://github.com/qinzheng93/GeoTransformer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SGA

Accuracy: 0.94. Result ID: 69924ebd3a6c3148490e0f30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ae1e209131cea4c7ad.md>)

[Implementation](<https://www.sota2.com/sgaligner.github.io>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SG-PGM

Accuracy: 0.33. Result ID: 69924ebd3a6c3148490e0f31.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d30.md>)

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

### SGPGM+R

Accuracy: 0.24. Result ID: 69924ebd3a6c3148490e0f32.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d30.md>)

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

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