# Stereo Matching on Synthetic surgical dataset Diffuse light (test)

Source: [Stereo Matching on Synthetic surgical dataset Diffuse light (test)](<https://www.sota2.com/research/sota/stereo-matching-on-synthetic-surgical-dataset-diffuse-light-test>)

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

Data updated: 2026-02-26T05:52:30.284Z

Evaluation of Stereo Matching performance on the test split of the Synthetic surgical dataset Diffuse light, reporting error statistics like Median Error, Mean Error, and the count of valid pixels.

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 | Stereo Matching |
| Dataset (including any stated split) | Synthetic surgical dataset Diffuse light (test) |
| Metric | Median Error |
| 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

- [Median Error](<https://www.sota2.com/research/sota/stereo-matching-on-synthetic-surgical-dataset-diffuse-light-test.md?metric=Median%20Error>): Lower is better; unit: SCALAR.

- [Mean Error](<https://www.sota2.com/research/sota/stereo-matching-on-synthetic-surgical-dataset-diffuse-light-test.md?metric=Mean%20Error>): Lower is better; unit: SCALAR.

- [Valid Pixels (x1000)](<https://www.sota2.com/research/sota/stereo-matching-on-synthetic-surgical-dataset-diffuse-light-test.md?metric=Valid%20Pixels%20(x1000)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Median Error | Result date | Report paper |
| --- | --- | --- | --- |
| BDIS | 0.161 | Not recorded | 68fa6d711e209131cea39ee7 |
| ELAS | 0.178 | Not recorded | 68fa6d711e209131cea39ee7 |
| DIS | 0.251 | Not recorded | 68fa6d711e209131cea39ee7 |
| PSMnet | 0.417 | Not recorded | 68fa6d711e209131cea39ee7 |
| SGBM | 0.512 | Not recorded | 68fa6d711e209131cea39ee7 |
| GwcNet | 0.542 | Not recorded | 68fa6d711e209131cea39ee7 |

### BDIS

Median Error: 0.161. Result ID: 698fa1fd3a6c314849fab1de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39ee7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39ee7.md>)

[Implementation](<https://github.com/JingweiSong/BDIS.git>)

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

### ELAS

Median Error: 0.178. Result ID: 698fa1fd3a6c314849fab1db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39ee7.md>)

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

### DIS

Median Error: 0.251. Result ID: 698fa1fd3a6c314849fab1dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39ee7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62611e209131ce9f8f95.md>)

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

### PSMnet

Median Error: 0.417. Result ID: 698fa1fd3a6c314849fab1e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39ee7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64271e209131cea02f27.md>)

[Implementation](<https://github.com/JiaRenChang/PSMNet>)

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

### SGBM

Median Error: 0.512. Result ID: 698fa1fd3a6c314849fab1dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39ee7.md>)

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

### GwcNet

Median Error: 0.542. Result ID: 698fa1fd3a6c314849fab1df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39ee7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa656e1e209131cea0a564.md>)

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

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