# Floor Plan Editing on Floor Plan Editing Dataset

Source: [Floor Plan Editing on Floor Plan Editing Dataset](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset>)

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

Data updated: 2026-03-13T08:18:25.893Z

Evaluation of models performing floor plan editing tasks on the Floor Plan Editing Dataset, measured using metrics like ΔIoU, ΔMSE, GED, and F1 scores.

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 | Floor Plan Editing |
| Dataset (including any stated split) | Floor Plan Editing Dataset |
| Metric | Micro IoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Micro IoU](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset.md?metric=Micro%20IoU>): Higher is better; unit: PERCENT.

- [Delta IoU](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset.md?metric=Delta%20IoU>): Higher is better; unit: PERCENT.

- [Delta MSE](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset.md?metric=Delta%20MSE>): Lower is better; unit: SCALAR.

- [Macro IoU](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset.md?metric=Macro%20IoU>): Higher is better; unit: PERCENT.

- [GED](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset.md?metric=GED>): Lower is better; unit: SCALAR.

- [Node F1 Score](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset.md?metric=Node%20F1%20Score>): Higher is better; unit: PERCENT.

- [Edge Overlap](<https://www.sota2.com/research/sota/floor-plan-editing-on-floor-plan-editing-dataset.md?metric=Edge%20Overlap>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Micro IoU | Result date | Report paper |
| --- | --- | --- | --- |
| Before edit | 88 | Not recorded | 69b399f60636e5bf4afbc9bd |
| HouseMind-E | 85.5 | Not recorded | 69b399f60636e5bf4afbc9bd |
| HouseMind-O | 84.4 | Not recorded | 69b399f60636e5bf4afbc9bd |
| Qwen-Image-Edit-2509 | 56.7 | Not recorded | 69b399f60636e5bf4afbc9bd |
| FLUX.1-Kontext-dev | 28.9 | Not recorded | 69b399f60636e5bf4afbc9bd |

### Before edit

Micro IoU: 88. Result ID: 69b3c7b147f34ce9249dbb5c.

[Reporting paper](<https://www.sota2.com/research/paper/69b399f60636e5bf4afbc9bd.md>)

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

### HouseMind-E

Micro IoU: 85.5. Result ID: 69b3c7b147f34ce9249dbb5f.

[Reporting paper](<https://www.sota2.com/research/paper/69b399f60636e5bf4afbc9bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b399f60636e5bf4afbc9bd.md>)

Recorded evaluation configuration: {"Time (s)":"∼3"}. This record does not assert independent reproduction.

### HouseMind-O

Micro IoU: 84.4. Result ID: 69b3c7b147f34ce9249dbb60.

[Reporting paper](<https://www.sota2.com/research/paper/69b399f60636e5bf4afbc9bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b399f60636e5bf4afbc9bd.md>)

Recorded evaluation configuration: {"Time (s)":"∼3"}. This record does not assert independent reproduction.

### Qwen-Image-Edit-2509

Micro IoU: 56.7. Result ID: 69b3c7b147f34ce9249dbb5e.

[Reporting paper](<https://www.sota2.com/research/paper/69b399f60636e5bf4afbc9bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a6a1e209131cea83137.md>)

Recorded evaluation configuration: {"Time (s)":"∼240"}. This record does not assert independent reproduction.

### FLUX.1-Kontext-dev

Micro IoU: 28.9. Result ID: 69b3c7b147f34ce9249dbb5d.

[Reporting paper](<https://www.sota2.com/research/paper/69b399f60636e5bf4afbc9bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a81e209131cea7eb79.md>)

Recorded evaluation configuration: {"Time (s)":"∼240"}. This record does not assert independent reproduction.

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