# 2D Visual Quality of Belief Prediction (Observed Scene) on AI2-THOR (test)

Source: [2D Visual Quality of Belief Prediction (Observed Scene) on AI2-THOR (test)](<https://www.sota2.com/research/sota/2d-visual-quality-of-belief-prediction-observed-scene-on-ai2-thor-test>)

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

Data updated: 2026-05-13T08:03:46.387Z

Evaluation of model performance on predicting the 2D visual quality of belief based on observed scenes within the AI2-THOR environment, measured using LPIPS, PSNR, and SSIM.

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 | 2D Visual Quality of Belief Prediction (Observed Scene) |
| Dataset (including any stated split) | AI2-THOR (test) |
| Metric | LPIPS |
| 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

- [LPIPS](<https://www.sota2.com/research/sota/2d-visual-quality-of-belief-prediction-observed-scene-on-ai2-thor-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/2d-visual-quality-of-belief-prediction-observed-scene-on-ai2-thor-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/2d-visual-quality-of-belief-prediction-observed-scene-on-ai2-thor-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | LPIPS | Result date | Report paper |
| --- | --- | --- | --- |
| 3D-Belief | 0.0502 | Not recorded | 6a0405b6dbc836b87d827683 |
| DFoT | 0.1206 | Not recorded | 6a0405b6dbc836b87d827683 |
| NWM | 0.1876 | Not recorded | 6a0405b6dbc836b87d827683 |

### 3D-Belief

LPIPS: 0.0502. Result ID: 6a042ffd47f34ce924e9eb2a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405b6dbc836b87d827683.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405b6dbc836b87d827683.md>)

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

### DFoT

LPIPS: 0.1206. Result ID: 6a042ffd47f34ce924e9eb29.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405b6dbc836b87d827683.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a291e209131cea816c0.md>)

Recorded evaluation configuration: {"training":"fine-tuned on AI2-THOR"}. This record does not assert independent reproduction.

### NWM

LPIPS: 0.1876. Result ID: 6a042ffd47f34ce924e9eb28.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405b6dbc836b87d827683.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ea1e209131cea75f91.md>)

[Implementation](<https://amirbar.net/nwm>)

Recorded evaluation configuration: {"training":"fine-tuned on AI2-THOR"}. This record does not assert independent reproduction.

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