# Image-Conditioned 3D Shape Generation on ShapeNet and 3D Cartoon Monster mixture (test)

Source: [Image-Conditioned 3D Shape Generation on ShapeNet and 3D Cartoon Monster mixture (test)](<https://www.sota2.com/research/sota/image-conditioned-3d-shape-generation-on-shapenet-and-3d-cartoon-monster-mixture-test>)

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

Data updated: 2026-02-26T06:02:54.844Z

Evaluation of models generating 3D shapes conditioned on input images, using a test split mixture of the ShapeNet and 3D Cartoon Monster datasets. Metrics include SI-S (ULIP/SITA), P-FID, and P-IS.

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 | Image-Conditioned 3D Shape Generation |
| Dataset (including any stated split) | ShapeNet and 3D Cartoon Monster mixture (test) |
| Metric | SI-S (ULIP) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [SI-S (ULIP)](<https://www.sota2.com/research/sota/image-conditioned-3d-shape-generation-on-shapenet-and-3d-cartoon-monster-mixture-test.md?metric=SI-S%20(ULIP)>): Higher is better; unit: SCALAR.

- [SI-S (SITA)](<https://www.sota2.com/research/sota/image-conditioned-3d-shape-generation-on-shapenet-and-3d-cartoon-monster-mixture-test.md?metric=SI-S%20(SITA)>): Higher is better; unit: SCALAR.

- [P-FID](<https://www.sota2.com/research/sota/image-conditioned-3d-shape-generation-on-shapenet-and-3d-cartoon-monster-mixture-test.md?metric=P-FID>): Lower is better; unit: SCALAR.

- [P-IS](<https://www.sota2.com/research/sota/image-conditioned-3d-shape-generation-on-shapenet-and-3d-cartoon-monster-mixture-test.md?metric=P-IS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | SI-S (ULIP) | Result date | Report paper |
| --- | --- | --- | --- |
| Michelangelo | 13.818 | Not recorded | 68fa6fe61e209131cea47fc9 |
| 3DS2V | 13.289 | Not recorded | 68fa6fe61e209131cea47fc9 |
| 3DILG | 9.134 | Not recorded | 68fa6fe61e209131cea47fc9 |

### Michelangelo

SI-S (ULIP): 13.818. Result ID: 6990f0f13a6c314849047560.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fc9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fc9.md>)

[Implementation](<https://github.com/NeuralCarver/Michelangelo>)

Recorded evaluation configuration: {"Conditioning":"Image-Conditioned"}. This record does not assert independent reproduction.

### 3DS2V

SI-S (ULIP): 13.289. Result ID: 6990f0f13a6c31484904755f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fc9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f371e209131cea4480d.md>)

Recorded evaluation configuration: {"Protocol":"Finetuned and Retrained","Conditioning":"Image-Conditioned"}. This record does not assert independent reproduction.

### 3DILG

SI-S (ULIP): 9.134. Result ID: 6990f0f13a6c31484904755e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fc9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da81e209131cea3b30e.md>)

Recorded evaluation configuration: {"Protocol":"Finetuned and Retrained","Conditioning":"Image-Conditioned"}. This record does not assert independent reproduction.

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