# Mesh Segmentation on COSEG (test)

Source: [Mesh Segmentation on COSEG (test)](<https://www.sota2.com/research/sota/mesh-segmentation-on-coseg-test>)

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

Data updated: 2026-02-26T06:08:11.182Z

Evaluation of Mesh Segmentation performance on the test split of the COSEG dataset, reporting category-specific scores.

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 | Mesh Segmentation |
| Dataset (including any stated split) | COSEG (test) |
| Metric | Vases |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

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

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

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

- [Mean Score](<https://www.sota2.com/research/sota/mesh-segmentation-on-coseg-test.md?metric=Mean%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Vases | Result date | Report paper |
| --- | --- | --- | --- |
| MeshWalker | 98.7 | Not recorded | 68fa68dc1e209131cea1ec32 |
| MeshCNN | 97.3 | Not recorded | 68fa68dc1e209131cea1ec32 |
| MeshCNN | 97.27 | Not recorded | 68fa65fc1e209131cea0dbac |
| MeshCNN | 96.64 | Not recorded | 68fa65fc1e209131cea0dbac |
| PointCNN | 96.4 | Not recorded | 68fa68dc1e209131cea1ec32 |
| PointCNN | 96.37 | Not recorded | 68fa65fc1e209131cea0dbac |
| PointNet++ | 94.7 | Not recorded | 68fa65fc1e209131cea0dbac |
| PointNet++ | 94.7 | Not recorded | 68fa68dc1e209131cea1ec32 |
| PointNet | 91.5 | Not recorded | 68fa65fc1e209131cea0dbac |

### MeshWalker

Vases: 98.7. Result ID: 698d8a7e8b517eb433223eda.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68dc1e209131cea1ec32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68dc1e209131cea1ec32.md>)

[Implementation](<https://github.com/AlonLahav/MeshWalker>)

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

### MeshCNN

Vases: 97.3. Result ID: 698d8a7e8b517eb433223edb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68dc1e209131cea1ec32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

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

### MeshCNN

Vases: 97.27. Result ID: 698cd5f78b517eb4331d119a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

Recorded evaluation configuration: {"Architecture":"U-Net (Pooling and Unpooling)"}. This record does not assert independent reproduction.

### MeshCNN

Vases: 96.64. Result ID: 698cd5f78b517eb4331d119b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

Recorded evaluation configuration: {"Pooling Strategy":"Random Pooling"}. This record does not assert independent reproduction.

### PointCNN

Vases: 96.4. Result ID: 698d8a7e8b517eb433223edd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68dc1e209131cea1ec32.md>)

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

### PointCNN

Vases: 96.37. Result ID: 698cd5f78b517eb4331d119e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e11e209131cea0d1ac.md>)

[Implementation](<https://github.com/WangYueFt/dgcnn>)

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

### PointNet++

Vases: 94.7. Result ID: 698cd5f78b517eb4331d119d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63641e209131ce9fe5a5.md>)

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

### PointNet++

Vases: 94.7. Result ID: 698d8a7e8b517eb433223edc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68dc1e209131cea1ec32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63641e209131ce9fe5a5.md>)

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

### PointNet

Vases: 91.5. Result ID: 698cd5f78b517eb4331d119c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dbac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634f1e209131ce9fe019.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.