# 3D Object Generation on Objaverse-LVIS 5,000-object (geometry-clean)

Source: [3D Object Generation on Objaverse-LVIS 5,000-object (geometry-clean)](<https://www.sota2.com/research/sota/3d-object-generation-on-objaverse-lvis-5-000-object-geometry-clean>)

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

Data updated: 2026-05-12T15:43:18.920Z

Evaluation of 3D Object Generation models using the geometry-cleaned 5,000-object subset of Objaverse-LVIS, assessed using fidelity metrics like Chamfer distance, Contamination, Separation, and Normal Consistency.

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 Generation |
| Dataset (including any stated split) | Objaverse-LVIS 5,000-object (geometry-clean) |
| Metric | Chamfer Distance |
| Unit | SCALAR |
| Direction | Lower 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

- [Chamfer Distance](<https://www.sota2.com/research/sota/3d-object-generation-on-objaverse-lvis-5-000-object-geometry-clean.md?metric=Chamfer%20Distance>): Lower is better; unit: SCALAR.

- [Contamination Score](<https://www.sota2.com/research/sota/3d-object-generation-on-objaverse-lvis-5-000-object-geometry-clean.md?metric=Contamination%20Score>): Lower is better; unit: SCALAR.

- [Separation Score](<https://www.sota2.com/research/sota/3d-object-generation-on-objaverse-lvis-5-000-object-geometry-clean.md?metric=Separation%20Score>): Higher is better; unit: SCALAR.

- [Normal Consistency](<https://www.sota2.com/research/sota/3d-object-generation-on-objaverse-lvis-5-000-object-geometry-clean.md?metric=Normal%20Consistency>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Chamfer Distance | Result date | Report paper |
| --- | --- | --- | --- |
| C2LT-3D | 0.0369 | Not recorded | 6a02b47bdbc836b87d824c2a |
| C2LT-3D | 0.0369 | Not recorded | 6a02b47bdbc836b87d824c2a |
| C2LT-3D | 0.0383 | Not recorded | 6a02b47bdbc836b87d824c2a |

### C2LT-3D

Chamfer Distance: 0.0369. Result ID: 6a034a8547f34ce924e88559.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

Recorded evaluation configuration: {"Checkpoint":"Seam Head Only"}. This record does not assert independent reproduction.

### C2LT-3D

Chamfer Distance: 0.0369. Result ID: 6a034a8547f34ce924e8855b.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

Recorded evaluation configuration: {"Checkpoint":"Component-Owned Realization"}. This record does not assert independent reproduction.

### C2LT-3D

Chamfer Distance: 0.0383. Result ID: 6a034a8547f34ce924e8855a.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

Recorded evaluation configuration: {"Checkpoint":"Learned Seam Prior"}. This record does not assert independent reproduction.

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