# Multi-View Reconstruction on Thingi32, DeepFashion3D, and Objaverse (test)

Source: [Multi-View Reconstruction on Thingi32, DeepFashion3D, and Objaverse (test)](<https://www.sota2.com/research/sota/multi-view-reconstruction-on-thingi32-deepfashion3d-and-objaverse-test>)

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

Data updated: 2026-02-26T05:39:00.411Z

Evaluation of Multi-View Reconstruction performance across the Thingi32, DeepFashion3D, and Objaverse datasets (test split), utilizing metrics such as Chamfer Distance (CD), F1 score, Normal Consistency (NC), and Edge Chamfer Distance (ECD).

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 | Multi-View Reconstruction |
| Dataset (including any stated split) | Thingi32, DeepFashion3D, and Objaverse (test) |
| Metric | Chamfer Distance |
| 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

- [Chamfer Distance](<https://www.sota2.com/research/sota/multi-view-reconstruction-on-thingi32-deepfashion3d-and-objaverse-test.md?metric=Chamfer%20Distance>): Lower is better; unit: SCALAR.

- [F1 Score](<https://www.sota2.com/research/sota/multi-view-reconstruction-on-thingi32-deepfashion3d-and-objaverse-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Normal Consistency (NC)](<https://www.sota2.com/research/sota/multi-view-reconstruction-on-thingi32-deepfashion3d-and-objaverse-test.md?metric=Normal%20Consistency%20(NC)>): Higher is better; unit: PERCENT.

- [Edge Chamfer Distance (ECD)](<https://www.sota2.com/research/sota/multi-view-reconstruction-on-thingi32-deepfashion3d-and-objaverse-test.md?metric=Edge%20Chamfer%20Distance%20(ECD)>): Lower is better; unit: SCALAR.

- [Edge F1 Score (EF1)](<https://www.sota2.com/research/sota/multi-view-reconstruction-on-thingi32-deepfashion3d-and-objaverse-test.md?metric=Edge%20F1%20Score%20(EF1)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Chamfer Distance | Result date | Report paper |
| --- | --- | --- | --- |
| DMesh | 0.000346 | Not recorded | 68fa79d71e209131cea7fab1 |
| FlexiCube | 0.00273 | Not recorded | 68fa79d71e209131cea7fab1 |
| NIE | 0.00585 | Not recorded | 68fa79d71e209131cea7fab1 |

### DMesh

Chamfer Distance: 0.000346. Result ID: 698b62347a967eddb76e27ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7fab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7fab1.md>)

[Implementation](<https://sonsang.github.io/dmesh-project>)

Recorded evaluation configuration: {"# Verts":"4.19K","# Faces":"8.80K","Time (sec)":"1434"}. This record does not assert independent reproduction.

### FlexiCube

Chamfer Distance: 0.00273. Result ID: 698b62347a967eddb76e27ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7fab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa704a1e209131cea4a3b2.md>)

Recorded evaluation configuration: {"# Verts":"10.9K","# Faces":"21.9K","Time (sec)":"56.47"}. This record does not assert independent reproduction.

### NIE

Chamfer Distance: 0.00585. Result ID: 698b62347a967eddb76e27ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7fab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1a1e209131cea37c23.md>)

Recorded evaluation configuration: {"# Verts":"74.5K","# Faces":"149K","Time (sec)":"6696"}. This record does not assert independent reproduction.

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