# 3D-Text Matching on Objaverse-LVIS 1.0 (test)

Source: [3D-Text Matching on Objaverse-LVIS 1.0 (test)](<https://www.sota2.com/research/sota/3d-text-matching-on-objaverse-lvis-1-0-test>)

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

Data updated: 2026-02-26T05:38:28.439Z

Evaluation of 3D-Text Matching performance on the test split of the Objaverse-LVIS 1.0 dataset, using language model-based accuracy metrics (CLIP, RoBERTa, BERT).

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-Text Matching |
| Dataset (including any stated split) | Objaverse-LVIS 1.0 (test) |
| Metric | CLIP Matching Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [CLIP Matching Accuracy](<https://www.sota2.com/research/sota/3d-text-matching-on-objaverse-lvis-1-0-test.md?metric=CLIP%20Matching%20Accuracy>): Higher is better; unit: PERCENT.

- [RoBERTa Matching Accuracy](<https://www.sota2.com/research/sota/3d-text-matching-on-objaverse-lvis-1-0-test.md?metric=RoBERTa%20Matching%20Accuracy>): Higher is better; unit: PERCENT.

- [BERT Matching Accuracy](<https://www.sota2.com/research/sota/3d-text-matching-on-objaverse-lvis-1-0-test.md?metric=BERT%20Matching%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CLIP Matching Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Affine + Subspace Projection | 67.6 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine + Subspace Projection | 65.6 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine + Subspace Projection | 61.4 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine + Subspace Projection | 30.8 | Not recorded | 68fa790f1e209131cea7be7e |
| Local CKA + Subspace Projection | 29.4 | Not recorded | 68fa790f1e209131cea7be7e |
| Local CKA + Subspace Projection | 26.8 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine + Subspace Projection | 25.2 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine + Subspace Projection | 21.4 | Not recorded | 68fa790f1e209131cea7be7e |
| Local CKA + Subspace Projection | 19 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine | 18.4 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine | 15.8 | Not recorded | 68fa790f1e209131cea7be7e |
| Affine | 11 | Not recorded | 68fa790f1e209131cea7be7e |
| Local CKA | 6.6 | Not recorded | 68fa790f1e209131cea7be7e |
| Local CKA | 5.8 | Not recorded | 68fa790f1e209131cea7be7e |
| Local CKA | 3.4 | Not recorded | 68fa790f1e209131cea7be7e |

### Affine + Subspace Projection

CLIP Matching Accuracy: 67.6. Result ID: 6995c18c3badfaffe6c424e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"OpenShape","3D Encoder Category":"Multi-modal"}. This record does not assert independent reproduction.

### Affine + Subspace Projection

CLIP Matching Accuracy: 65.6. Result ID: 6995c18c3badfaffe6c424e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"ULIP-2","3D Encoder Category":"Multi-modal"}. This record does not assert independent reproduction.

### Affine + Subspace Projection

CLIP Matching Accuracy: 61.4. Result ID: 6995c18c3badfaffe6c424e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"Uni3D","3D Encoder Category":"Multi-modal"}. This record does not assert independent reproduction.

### Affine + Subspace Projection

CLIP Matching Accuracy: 30.8. Result ID: 6995c18c3badfaffe6c424ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"PointBert","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Local CKA + Subspace Projection

CLIP Matching Accuracy: 29.4. Result ID: 6995c18c3badfaffe6c424f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"PointBert","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Local CKA + Subspace Projection

CLIP Matching Accuracy: 26.8. Result ID: 6995c18c3badfaffe6c424f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"Pointnet","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Affine + Subspace Projection

CLIP Matching Accuracy: 25.2. Result ID: 6995c18c3badfaffe6c424ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"Pointnet","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Affine + Subspace Projection

CLIP Matching Accuracy: 21.4. Result ID: 6995c18c3badfaffe6c424ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"SparseConv","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Local CKA + Subspace Projection

CLIP Matching Accuracy: 19. Result ID: 6995c18c3badfaffe6c424f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Implementation](<https://github.com/Souhail-01/3d-text-alignment>)

Recorded evaluation configuration: {"3D Encoder":"SparseConv","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Affine

CLIP Matching Accuracy: 18.4. Result ID: 6995c18c3badfaffe6c424eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa722a1e209131cea54e66.md>)

[Implementation](<https://github.com/Flegyas/latent-translation>)

Recorded evaluation configuration: {"3D Encoder":"Pointnet","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Affine

CLIP Matching Accuracy: 15.8. Result ID: 6995c18c3badfaffe6c424e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa722a1e209131cea54e66.md>)

[Implementation](<https://github.com/Flegyas/latent-translation>)

Recorded evaluation configuration: {"3D Encoder":"PointBert","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Affine

CLIP Matching Accuracy: 11. Result ID: 6995c18c3badfaffe6c424ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa722a1e209131cea54e66.md>)

[Implementation](<https://github.com/Flegyas/latent-translation>)

Recorded evaluation configuration: {"3D Encoder":"SparseConv","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Local CKA

CLIP Matching Accuracy: 6.6. Result ID: 6995c18c3badfaffe6c424f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a31e209131cea57ba1.md>)

[Implementation](<https://www.sota2.com/github.com/mayug/0-shot-llm-vision>)

Recorded evaluation configuration: {"3D Encoder":"Pointnet","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Local CKA

CLIP Matching Accuracy: 5.8. Result ID: 6995c18c3badfaffe6c424ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a31e209131cea57ba1.md>)

[Implementation](<https://www.sota2.com/github.com/mayug/0-shot-llm-vision>)

Recorded evaluation configuration: {"3D Encoder":"PointBert","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

### Local CKA

CLIP Matching Accuracy: 3.4. Result ID: 6995c18c3badfaffe6c424f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa790f1e209131cea7be7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a31e209131cea57ba1.md>)

[Implementation](<https://www.sota2.com/github.com/mayug/0-shot-llm-vision>)

Recorded evaluation configuration: {"3D Encoder":"SparseConv","3D Encoder Category":"Uni-modal"}. This record does not assert independent reproduction.

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