# Text-conditioned 3D asset generation on G-Objaverse (evaluation)

Source: [Text-conditioned 3D asset generation on G-Objaverse (evaluation)](<https://www.sota2.com/research/sota/text-conditioned-3d-asset-generation-on-g-objaverse-evaluation>)

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

Data updated: 2026-04-07T09:28:36.578Z

Evaluation of Text-conditioned 3D asset generation models on the G-Objaverse dataset (evaluation split), assessed using FID, FIDmat, IS, and CLIP 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 | Text-conditioned 3D asset generation |
| Dataset (including any stated split) | G-Objaverse (evaluation) |
| Metric | IS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [IS](<https://www.sota2.com/research/sota/text-conditioned-3d-asset-generation-on-g-objaverse-evaluation.md?metric=IS>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/text-conditioned-3d-asset-generation-on-g-objaverse-evaluation.md?metric=FID>): Lower is better; unit: SCALAR.

- [FIDmat](<https://www.sota2.com/research/sota/text-conditioned-3d-asset-generation-on-g-objaverse-evaluation.md?metric=FIDmat>): Lower is better; unit: SCALAR.

- [CLIP Score](<https://www.sota2.com/research/sota/text-conditioned-3d-asset-generation-on-g-objaverse-evaluation.md?metric=CLIP%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | IS | Result date | Report paper |
| --- | --- | --- | --- |
| MVD-v2.1-3D | 14.63 | Not recorded | 68fa7b2b1e209131cea86faf |
| DV-3D | 13.91 | Not recorded | 68fa7b2b1e209131cea86faf |
| DiffSplat | 13.75 | Not recorded | 68fa7b2b1e209131cea86faf |
| LGM | 13.53 | Not recorded | 68fa7b2b1e209131cea86faf |
| TRELLIS | 13.4 | Not recorded | 68fa7b2b1e209131cea86faf |
| MVD-v1.5-3D | 12.88 | Not recorded | 68fa7b2b1e209131cea86faf |
| LaRa | 12.77 | Not recorded | 68fa7b2b1e209131cea86faf |
| 3DTopia-XL | 9.42 | Not recorded | 68fa7b2b1e209131cea86faf |

### MVD-v2.1-3D

IS: 14.63. Result ID: 69d4ce4347f34ce924bce9f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

Recorded evaluation configuration: {"Base Multi-view Diffusion Model":"MVDream 2.1","Adapter":"LGAA"}. This record does not assert independent reproduction.

### DV-3D

IS: 13.91. Result ID: 69d4ce4347f34ce924bce9f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

Recorded evaluation configuration: {"Base Multi-view Diffusion Model":"Dreamview","Adapter":"LGAA"}. This record does not assert independent reproduction.

### DiffSplat

IS: 13.75. Result ID: 69d4ce4347f34ce924bce9f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76b61e209131cea6ea4c.md>)

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

### LGM

IS: 13.53. Result ID: 69d4ce4347f34ce924bce9f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72291e209131cea54dd3.md>)

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

### TRELLIS

IS: 13.4. Result ID: 69d4ce4347f34ce924bce9f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b608.md>)

[Implementation](<https://trellis3d.github.io/>)

Recorded evaluation configuration: {"PBR Material Generation Pipeline":"TexGaussian"}. This record does not assert independent reproduction.

### MVD-v1.5-3D

IS: 12.88. Result ID: 69d4ce4347f34ce924bce9f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

Recorded evaluation configuration: {"Base Multi-view Diffusion Model":"MVDream 1.5","Adapter":"LGAA"}. This record does not assert independent reproduction.

### LaRa

IS: 12.77. Result ID: 69d4ce4347f34ce924bce9f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa742a1e209131cea6025c.md>)

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

### 3DTopia-XL

IS: 9.42. Result ID: 69d4ce4347f34ce924bce9f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b2b1e209131cea86faf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737ba.md>)

[Implementation](<https://3dtopia.github.io/3DTopia-XL/>)

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.