# Glass Segmentation on GDD 4 (test)

Source: [Glass Segmentation on GDD 4 (test)](<https://www.sota2.com/research/sota/glass-segmentation-on-gdd-4-test>)

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

Data updated: 2026-02-26T05:49:00.363Z

Evaluation of Glass Segmentation performance on the test split of the GDD 4 dataset, reporting metrics such as MAE, IOU, and BER.

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 | Glass Segmentation |
| Dataset (including any stated split) | GDD 4 (test) |
| Metric | MAE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [MAE](<https://www.sota2.com/research/sota/glass-segmentation-on-gdd-4-test.md?metric=MAE>): Lower is better; unit: SCALAR.

- [mIoU](<https://www.sota2.com/research/sota/glass-segmentation-on-gdd-4-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [BER](<https://www.sota2.com/research/sota/glass-segmentation-on-gdd-4-test.md?metric=BER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | MAE | Result date | Report paper |
| --- | --- | --- | --- |
| Ours (RGB-only) | 0.072 | Not recorded | 68fa6ec61e209131cea41f9f |
| EBLNet | 0.074 | Not recorded | 68fa6ec61e209131cea41f9f |
| Translab | 0.081 | Not recorded | 68fa6ec61e209131cea41f9f |
| GDNet | 0.088 | Not recorded | 68fa6ec61e209131cea41f9f |
| MirrorNet | 0.094 | Not recorded | 68fa6ec61e209131cea41f9f |

### Ours (RGB-only)

MAE: 0.072. Result ID: 6990400d3a6c314849ff395f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ec61e209131cea41f9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ec61e209131cea41f9f.md>)

[Implementation](<https://github.com/Dong-Huo/RGB-T-Glass-Segmentation>)

Recorded evaluation configuration: {"Input":"RGB"}. This record does not assert independent reproduction.

### EBLNet

MAE: 0.074. Result ID: 6990400d3a6c314849ff395e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ec61e209131cea41f9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Implementation](<https://github.com/hehao13/EBLNet>)

Recorded evaluation configuration: {"Input":"RGB"}. This record does not assert independent reproduction.

### Translab

MAE: 0.081. Result ID: 6990400d3a6c314849ff395d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ec61e209131cea41f9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68141e209131cea1a0ad.md>)

[Implementation](<https://www.sota2.com/github.com/xieenze/Segment_Transparent_Objects>)

Recorded evaluation configuration: {"Input":"RGB"}. This record does not assert independent reproduction.

### GDNet

MAE: 0.088. Result ID: 6990400d3a6c314849ff395c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ec61e209131cea41f9f.md>)

Recorded evaluation configuration: {"Input":"RGB"}. This record does not assert independent reproduction.

### MirrorNet

MAE: 0.094. Result ID: 6990400d3a6c314849ff395b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ec61e209131cea41f9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66751e209131cea10386.md>)

[Implementation](<https://mhaiyang.github.io/ICCV2019_MirrorNet/index>)

Recorded evaluation configuration: {"Input":"RGB"}. This record does not assert independent reproduction.

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