# Image Alignment on DH-temple (train test overlapping)

Source: [Image Alignment on DH-temple (train test overlapping)](<https://www.sota2.com/research/sota/image-alignment-on-dh-temple-train-test-overlapping>)

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

Data updated: 2026-02-26T06:00:16.446Z

Evaluation of Image Alignment performance on the DH-temple dataset, specifically using the train/test overlapping split, measured by RMSE (Training/Test) and outlier percentage.

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 Alignment |
| Dataset (including any stated split) | DH-temple (train test overlapping) |
| Metric | RMSE (Training) |
| 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

- [RMSE (Training)](<https://www.sota2.com/research/sota/image-alignment-on-dh-temple-train-test-overlapping.md?metric=RMSE%20(Training)>): Lower is better; unit: SCALAR.

- [RMSE (Test)](<https://www.sota2.com/research/sota/image-alignment-on-dh-temple-train-test-overlapping.md?metric=RMSE%20(Test)>): Lower is better; unit: SCALAR.

- [Outlier Percentage](<https://www.sota2.com/research/sota/image-alignment-on-dh-temple-train-test-overlapping.md?metric=Outlier%20Percentage>): Lower is better; unit: PERCENT.

## Recorded results

| Method | RMSE (Training) | Result date | Report paper |
| --- | --- | --- | --- |
| Mesh-based Warp | 4.84 | Not recorded | 68fa66581e209131cea0faae |
| Mesh-based Warp | 4.84 | Not recorded | 68fa66581e209131cea0faae |
| APAP | 5.95 | Not recorded | 68fa66581e209131cea0faae |
| APAP | 5.95 | Not recorded | 68fa66581e209131cea0faae |
| Homography | 7.84 | Not recorded | 68fa66581e209131cea0faae |
| Homography | 7.84 | Not recorded | 68fa66581e209131cea0faae |

### Mesh-based Warp

RMSE (Training): 4.84. Result ID: 698ceb2d8b517eb4331dac9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

Recorded evaluation configuration: {"dual-feature":false,"grid size":"40x40"}. This record does not assert independent reproduction.

### Mesh-based Warp

RMSE (Training): 4.84. Result ID: 698ceb2d8b517eb4331dac9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

Recorded evaluation configuration: {"dual-feature":true,"grid size":"40x40"}. This record does not assert independent reproduction.

### APAP

RMSE (Training): 5.95. Result ID: 698ceb2d8b517eb4331dac9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

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

### APAP

RMSE (Training): 5.95. Result ID: 698ceb2d8b517eb4331dac9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

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

### Homography

RMSE (Training): 7.84. Result ID: 698ceb2d8b517eb4331dac98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

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

### Homography

RMSE (Training): 7.84. Result ID: 698ceb2d8b517eb4331dac99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faae.md>)

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

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