# Unconditional 3D Object Generation on ShapeNet cars (test)

Source: [Unconditional 3D Object Generation on ShapeNet cars (test)](<https://www.sota2.com/research/sota/unconditional-3d-object-generation-on-shapenet-cars-test>)

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

Data updated: 2026-02-26T05:44:33.071Z

Evaluation of models performing Unconditional 3D Object Generation on the test split of the ShapeNet Cars category, measured using distribution metrics like FID and KID.

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 | Unconditional 3D Object Generation |
| Dataset (including any stated split) | ShapeNet cars (test) |
| Metric | FID |
| 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

- [FID](<https://www.sota2.com/research/sota/unconditional-3d-object-generation-on-shapenet-cars-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [KID](<https://www.sota2.com/research/sota/unconditional-3d-object-generation-on-shapenet-cars-test.md?metric=KID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| UVGS | 26.2 | Not recorded | 68fa77931e209131cea74147 |
| GaussianCube | 34.67 | Not recorded | 68fa77931e209131cea74147 |
| Get3D | 53.17 | Not recorded | 68fa77931e209131cea74147 |
| EG3D | 74.51 | Not recorded | 68fa77931e209131cea74147 |
| DiffTF | 84.57 | Not recorded | 68fa77931e209131cea74147 |

### UVGS

FID: 26.2. Result ID: 6995448a3badfaffe6318bfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea74147.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77931e209131cea74147.md>)

[Implementation](<https://aashishrai3799.github.io/uvgs>)

Recorded evaluation configuration: {"Generated samples":"20K"}. This record does not assert independent reproduction.

### GaussianCube

FID: 34.67. Result ID: 6995448a3badfaffe6318bfb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea74147.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757a1e209131cea683c7.md>)

[Implementation](<https://gaussiancube.github.io/>)

Recorded evaluation configuration: {"Generated samples":"20K"}. This record does not assert independent reproduction.

### Get3D

FID: 53.17. Result ID: 6995448a3badfaffe6318bf8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea74147.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d891e209131cea3a723.md>)

Recorded evaluation configuration: {"Generated samples":"20K"}. This record does not assert independent reproduction.

### EG3D

FID: 74.51. Result ID: 6995448a3badfaffe6318bfa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea74147.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c6a1e209131cea33f96.md>)

Recorded evaluation configuration: {"Generated samples":"20K"}. This record does not assert independent reproduction.

### DiffTF

FID: 84.57. Result ID: 6995448a3badfaffe6318bf9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea74147.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70901e209131cea4bd5e.md>)

Recorded evaluation configuration: {"Generated samples":"20K"}. This record does not assert independent reproduction.

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