# Scene-level reconstruction on synthetic indoor scene dataset

Source: [Scene-level reconstruction on synthetic indoor scene dataset](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-indoor-scene-dataset>)

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

Data updated: 2026-02-26T05:47:19.132Z

Evaluation of models performing scene-level 3D reconstruction using the synthetic indoor scene dataset, measured by IoU, Chamfer-L1 distance, Normal Consistency, and F-score.

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 | Scene-level reconstruction |
| Dataset (including any stated split) | synthetic indoor scene dataset |
| Metric | IoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [IoU](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-indoor-scene-dataset.md?metric=IoU>): Higher is better; unit: PERCENT.

- [Chamfer-L1](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-indoor-scene-dataset.md?metric=Chamfer-L1>): Lower is better; unit: SCALAR.

- [Normal Consistency](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-indoor-scene-dataset.md?metric=Normal%20Consistency>): Higher is better; unit: PERCENT.

- [F-score](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-synthetic-indoor-scene-dataset.md?metric=F-score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | IoU | Result date | Report paper |
| --- | --- | --- | --- |
| Dynamic Plane Convolutional Occupancy Networks | 83.7 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 83.1 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 83.1 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 81.9 | Not recorded | 68fa68b71e209131cea1dae6 |
| ConvONet | 81.6 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 81.4 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 81 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 80 | Not recorded | 68fa68b71e209131cea1dae6 |
| ConvONet | 79.7 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 79.7 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 79.5 | Not recorded | 68fa68b71e209131cea1dae6 |
| Dynamic Plane Convolutional Occupancy Networks | 79.1 | Not recorded | 68fa68b71e209131cea1dae6 |
| ConvONet | 78.9 | Not recorded | 68fa68b71e209131cea1dae6 |
| ONet | 47.5 | Not recorded | 68fa68b71e209131cea1dae6 |

### Dynamic Plane Convolutional Occupancy Networks

IoU: 83.7. Result ID: 698d7eb88b517eb43321ef56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"Without","planes":"3 Canonical + 2 Dynamic"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 83.1. Result ID: 698d7eb88b517eb43321ef57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"Without","planes":"3 Canonical + 4 Dynamic"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 83.1. Result ID: 698d7eb88b517eb43321ef5d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"With","planes":"3 Canonical + 4 Dynamic"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 81.9. Result ID: 698d7eb88b517eb43321ef5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"With","planes":"7 Dynamic"}. This record does not assert independent reproduction.

### ConvONet

IoU: 81.6. Result ID: 698d7eb88b517eb43321ef52.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68131e209131cea1a017.md>)

Recorded evaluation configuration: {"positional encoding":"Without","planes":"3 Canonical","grid resolution":"32^3"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 81.4. Result ID: 698d7eb88b517eb43321ef59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"With","planes":"3 Dynamic"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 81. Result ID: 698d7eb88b517eb43321ef55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"Without","planes":"7 Dynamic"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 80. Result ID: 698d7eb88b517eb43321ef5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"With","planes":"5 Dynamic"}. This record does not assert independent reproduction.

### ConvONet

IoU: 79.7. Result ID: 698d7eb88b517eb43321ef58.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68131e209131cea1a017.md>)

Recorded evaluation configuration: {"positional encoding":"With","planes":"3 Canonical"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 79.7. Result ID: 698d7eb88b517eb43321ef5c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"With","planes":"3 Canonical + 2 Dynamic"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 79.5. Result ID: 698d7eb88b517eb43321ef53.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"Without","planes":"3 Dynamic"}. This record does not assert independent reproduction.

### Dynamic Plane Convolutional Occupancy Networks

IoU: 79.1. Result ID: 698d7eb88b517eb43321ef54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Implementation](<https://github.com/dsvilarkovic/dynamic_plane_convolutional_onet>)

Recorded evaluation configuration: {"positional encoding":"Without","planes":"5 Dynamic"}. This record does not assert independent reproduction.

### ConvONet

IoU: 78.9. Result ID: 698d7eb88b517eb43321ef51.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68131e209131cea1a017.md>)

Recorded evaluation configuration: {"positional encoding":"Without","planes":"3 Canonical"}. This record does not assert independent reproduction.

### ONet

IoU: 47.5. Result ID: 698d7eb88b517eb43321ef50.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dae6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a71e209131cea0ba34.md>)

Recorded evaluation configuration: {"positional encoding":"Without"}. This record does not assert independent reproduction.

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