# Depth distribution prediction on 88 indoor panoramas (test)

Source: [Depth distribution prediction on 88 indoor panoramas (test)](<https://www.sota2.com/research/sota/depth-distribution-prediction-on-88-indoor-panoramas-test>)

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

Data updated: 2026-02-26T05:48:00.711Z

Evaluation of depth distribution prediction performance on the test split of the 88 indoor panoramas dataset, measured using L2 distance and cosine distance.

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 | Depth distribution prediction |
| Dataset (including any stated split) | 88 indoor panoramas (test) |
| Metric | L2 Distance |
| Unit | SCALAR |
| Direction | Lower 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

- [L2 Distance](<https://www.sota2.com/research/sota/depth-distribution-prediction-on-88-indoor-panoramas-test.md?metric=L2%20Distance>): Lower is better; unit: SCALAR.

- [Cosine Distance](<https://www.sota2.com/research/sota/depth-distribution-prediction-on-88-indoor-panoramas-test.md?metric=Cosine%20Distance>): Lower is better; unit: SCALAR.

## Recorded results

| Method | L2 Distance | Result date | Report paper |
| --- | --- | --- | --- |
| LayoutNet | 18.51 | Not recorded | 68fa642e1e209131cea03377 |
| Yang et al. | 27.02 | Not recorded | 68fa642e1e209131cea03377 |

### LayoutNet

L2 Distance: 18.51. Result ID: 698c164df729bc7f68e83994.

[Reporting paper](<https://www.sota2.com/research/paper/68fa642e1e209131cea03377.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642e1e209131cea03377.md>)

[Implementation](<https://github.com/zouchuhang/LayoutNet>)

Recorded evaluation configuration: {"training":"PanoContext + optimization","mode":"full cuboid layout prediction"}. This record does not assert independent reproduction.

### Yang et al.

L2 Distance: 27.02. Result ID: 698c164df729bc7f68e83993.

[Reporting paper](<https://www.sota2.com/research/paper/68fa642e1e209131cea03377.md>)

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.
