# Semantic Part Completion on Scan2CAD

Source: [Semantic Part Completion on Scan2CAD](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad>)

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

Data updated: 2026-02-26T05:38:11.320Z

Evaluation of Semantic Part Completion performance on the Scan2CAD dataset, reporting Chamfer Distance metrics for accuracy and completion across various object categories (chair, table, etc.).

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 | Semantic Part Completion |
| Dataset (including any stated split) | Scan2CAD |
| Metric | CD Accuracy (chair) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [CD Accuracy (chair)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(chair)>): Lower is better; unit: SCALAR.

- [CD Accuracy (table)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(table)>): Lower is better; unit: SCALAR.

- [CD Accuracy (cab.)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(cab.)>): Lower is better; unit: SCALAR.

- [CD Accuracy (bkshlf)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(bkshlf)>): Lower is better; unit: SCALAR.

- [CD Accuracy (bed)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(bed)>): Lower is better; unit: SCALAR.

- [CD Accuracy (bin)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(bin)>): Lower is better; unit: SCALAR.

- [CD Accuracy (class avg)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(class%20avg)>): Lower is better; unit: SCALAR.

- [CD Accuracy (inst avg)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Accuracy%20(inst%20avg)>): Lower is better; unit: SCALAR.

- [CD Completion (chair)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(chair)>): Lower is better; unit: SCALAR.

- [CD Completion (table)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(table)>): Lower is better; unit: SCALAR.

- [CD Completion (cab.)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(cab.)>): Lower is better; unit: SCALAR.

- [CD Completion (bkshlf)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(bkshlf)>): Lower is better; unit: SCALAR.

- [CD Completion (bed)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(bed)>): Lower is better; unit: SCALAR.

- [CD Completion (bin)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(bin)>): Lower is better; unit: SCALAR.

- [CD Completion (class avg)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(class%20avg)>): Lower is better; unit: SCALAR.

- [CD Completion (inst avg)](<https://www.sota2.com/research/sota/semantic-part-completion-on-scan2cad.md?metric=CD%20Completion%20(inst%20avg)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | CD Accuracy (chair) | Result date | Report paper |
| --- | --- | --- | --- |
| Neural Part Priors | 0.013 | Not recorded | 68fa6ee71e209131cea42c73 |
| MLCVNet + StructureNet | 0.024 | Not recorded | 68fa6ee71e209131cea42c73 |
| Bokhovkin et al. | 0.029 | Not recorded | 68fa6ee71e209131cea42c73 |
| SG-NN + MLCVNet + PointGroup | 0.047 | Not recorded | 68fa6ee71e209131cea42c73 |

### Neural Part Priors

CD Accuracy (chair): 0.013. Result ID: 69906c0b3a6c314849007136.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c73.md>)

[Implementation](<https://www.sota2.com/alexeybokhovkin.github.io/neural-part-priors/>)

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

### MLCVNet + StructureNet

CD Accuracy (chair): 0.024. Result ID: 69906c0b3a6c314849007134.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c73.md>)

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

### Bokhovkin et al.

CD Accuracy (chair): 0.029. Result ID: 69906c0b3a6c314849007135.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68db1e209131cea1eb42.md>)

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

### SG-NN + MLCVNet + PointGroup

CD Accuracy (chair): 0.047. Result ID: 69906c0b3a6c314849007133.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c73.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.