# 3D Visual Question Answering on 3DMV-VQA (single room subset)

Source: [3D Visual Question Answering on 3DMV-VQA (single room subset)](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-3dmv-vqa-single-room-subset>)

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

Data updated: 2026-02-26T05:39:44.195Z

Evaluation of 3D Visual Question Answering performance specifically on the single room subset (1,212 scenes) of the 3DMV-VQA dataset, using metrics for Concept, Counting, Relation, Comparison, and Overall accuracy.

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 Visual Question Answering |
| Dataset (including any stated split) | 3DMV-VQA single room only subset of 1,212 scenes |
| Metric | Concept Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Concept Accuracy](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-3dmv-vqa-single-room-subset.md?metric=Concept%20Accuracy>): Higher is better; unit: PERCENT.

- [Counting Accuracy](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-3dmv-vqa-single-room-subset.md?metric=Counting%20Accuracy>): Higher is better; unit: PERCENT.

- [Relation Accuracy](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-3dmv-vqa-single-room-subset.md?metric=Relation%20Accuracy>): Higher is better; unit: PERCENT.

- [Comparison Accuracy](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-3dmv-vqa-single-room-subset.md?metric=Comparison%20Accuracy>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-3dmv-vqa-single-room-subset.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Concept Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Scene-LLM | 70.2 | Not recorded | 68fa729a1e209131cea576f4 |
| Scene-LLM | 69.9 | Not recorded | 68fa729a1e209131cea576f4 |

### Scene-LLM

Concept Accuracy: 70.2. Result ID: 699247213a6c3148490dd5db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa729a1e209131cea576f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729a1e209131cea576f4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"task-specific tuning (tt)"}. This record does not assert independent reproduction.

### Scene-LLM

Concept Accuracy: 69.9. Result ID: 699247213a6c3148490dd5da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa729a1e209131cea576f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729a1e209131cea576f4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"zero-shot (zs)"}. This record does not assert independent reproduction.

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