# 3D Object Completion on 3D-RecGAN real-world (test)

Source: [3D Object Completion on 3D-RecGAN real-world (test)](<https://www.sota2.com/research/sota/3d-object-completion-on-3d-recgan-real-world-test>)

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

Data updated: 2026-02-26T05:54:32.814Z

Evaluation of 3D object completion performance on the test split of the 3D-RecGAN real-world dataset, reporting metrics for specific object categories like chair, couch, and table, along with an overall average score.

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 | 3D object completion |
| Dataset (including any stated split) | 3D-RecGAN real-world (test) |
| Metric | Overall Score |
| 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

- [Overall Score](<https://www.sota2.com/research/sota/3d-object-completion-on-3d-recgan-real-world-test.md?metric=Overall%20Score>): Lower is better; unit: SCALAR.

- [Chair Score](<https://www.sota2.com/research/sota/3d-object-completion-on-3d-recgan-real-world-test.md?metric=Chair%20Score>): Lower is better; unit: SCALAR.

- [Couch Score](<https://www.sota2.com/research/sota/3d-object-completion-on-3d-recgan-real-world-test.md?metric=Couch%20Score>): Lower is better; unit: SCALAR.

- [Table Score](<https://www.sota2.com/research/sota/3d-object-completion-on-3d-recgan-real-world-test.md?metric=Table%20Score>): Lower is better; unit: SCALAR.

- [Average Score](<https://www.sota2.com/research/sota/3d-object-completion-on-3d-recgan-real-world-test.md?metric=Average%20Score>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Overall Score | Result date | Report paper |
| --- | --- | --- | --- |
| Han et al. | 18.4 | Not recorded | 68fa6c771e209131cea34199 |
| 3D-RecGAN | 23 | Not recorded | 68fa6c771e209131cea34199 |
| 3D-RecAE | 23.1 | Not recorded | 68fa6c771e209131cea34199 |
| ForkNet | 26.1 | Not recorded | 68fa6c771e209131cea34199 |
| ForkNet | 32.7 | Not recorded | 68fa6c771e209131cea34199 |

### Han et al.

Overall Score: 18.4. Result ID: 698f15d23a6c314849f5a42c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c771e209131cea34199.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63a31e209131ce9fff24.md>)

Recorded evaluation configuration: {"Resolution":"64x64x64","Evaluation protocol":"single category test"}. This record does not assert independent reproduction.

### 3D-RecGAN

Overall Score: 23. Result ID: 698f15d23a6c314849f5a42e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c771e209131cea34199.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c31e209131cea06665.md>)

Recorded evaluation configuration: {"Resolution":"64x64x64","Evaluation protocol":"single category test"}. This record does not assert independent reproduction.

### 3D-RecAE

Overall Score: 23.1. Result ID: 698f15d23a6c314849f5a42d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c771e209131cea34199.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c31e209131cea06665.md>)

Recorded evaluation configuration: {"Resolution":"64x64x64","Evaluation protocol":"single category test"}. This record does not assert independent reproduction.

### ForkNet

Overall Score: 26.1. Result ID: 698f15d23a6c314849f5a430.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c771e209131cea34199.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c771e209131cea34199.md>)

Recorded evaluation configuration: {"Resolution":"64x64x64","Evaluation protocol":"single category test","scene consistency":false}. This record does not assert independent reproduction.

### ForkNet

Overall Score: 32.7. Result ID: 698f15d23a6c314849f5a42f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c771e209131cea34199.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c771e209131cea34199.md>)

Recorded evaluation configuration: {"Resolution":"64x64x64","Evaluation protocol":"single category test","scene consistency":true}. This record does not assert independent reproduction.

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