# Image-to-point cloud registration on Oxford (test)

Source: [Image-to-point cloud registration on Oxford (test)](<https://www.sota2.com/research/sota/image-to-point-cloud-registration-on-oxford-test>)

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

Data updated: 2026-02-26T06:00:51.354Z

Evaluation of Image-to-point cloud registration performance on the test split of the Oxford dataset, reporting alignment errors such as RTE and RRE.

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 | Image-to-point cloud registration |
| Dataset (including any stated split) | Oxford (test) |
| Metric | RTE (m) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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

- [RTE (m)](<https://www.sota2.com/research/sota/image-to-point-cloud-registration-on-oxford-test.md?metric=RTE%20(m)>): Lower is better; unit: SCALAR.

- [RRE (°)](<https://www.sota2.com/research/sota/image-to-point-cloud-registration-on-oxford-test.md?metric=RRE%20(%C2%B0)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | RTE (m) | Result date | Report paper |
| --- | --- | --- | --- |
| MonoDepth2 + GT-ICP | 1.3 | Not recorded | 68fa69b01e209131cea23682 |
| 2D3D-MatchNet | 1.41 | Not recorded | 68fa69b01e209131cea23682 |
| Frus. Cls. + Inv.Proj. 2D | 1.65 | Not recorded | 68fa69b01e209131cea23682 |
| Grid Cls. + PnP | 1.91 | Not recorded | 68fa69b01e209131cea23682 |
| Frus. Cls. + Inv.Proj. 3D | 2.27 | Not recorded | 68fa69b01e209131cea23682 |
| Direct Regression | 5.02 | Not recorded | 68fa69b01e209131cea23682 |
| MonoDepth2 + USIP | 33.2 | Not recorded | 68fa69b01e209131cea23682 |

### MonoDepth2 + GT-ICP

RTE (m): 1.3. Result ID: 698dd2ec8b517eb43323fac3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

Recorded evaluation configuration: {"initialization":"ground truth relative pose"}. This record does not assert independent reproduction.

### 2D3D-MatchNet

RTE (m): 1.41. Result ID: 698dd2ec8b517eb43323fac4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a91e209131cea0bb4c.md>)

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

### Frus. Cls. + Inv.Proj. 2D

RTE (m): 1.65. Result ID: 698dd2ec8b517eb43323fac7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

[Implementation](<https://github.com/lijx10/DeepI2P>)

Recorded evaluation configuration: {"variant":"DeepI2P"}. This record does not assert independent reproduction.

### Grid Cls. + PnP

RTE (m): 1.91. Result ID: 698dd2ec8b517eb43323fac5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

[Implementation](<https://github.com/lijx10/DeepI2P>)

Recorded evaluation configuration: {"variant":"DeepI2P"}. This record does not assert independent reproduction.

### Frus. Cls. + Inv.Proj. 3D

RTE (m): 2.27. Result ID: 698dd2ec8b517eb43323fac6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

[Implementation](<https://github.com/lijx10/DeepI2P>)

Recorded evaluation configuration: {"variant":"DeepI2P"}. This record does not assert independent reproduction.

### Direct Regression

RTE (m): 5.02. Result ID: 698dd2ec8b517eb43323fac1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

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

### MonoDepth2 + USIP

RTE (m): 33.2. Result ID: 698dd2ec8b517eb43323fac2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b01e209131cea23682.md>)

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

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