# 3D Reconstruction on Pix3D 10% of the data (test)

Source: [3D Reconstruction on Pix3D 10% of the data (test)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test>)

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

Data updated: 2026-02-26T05:47:56.785Z

Evaluation of 3D Reconstruction performance using a specific 10% subset of the Pix3D test data, reporting category-specific L1 Chamfer Distance (CD).

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 | 3D Reconstruction |
| Dataset (including any stated split) | Pix3D 10% of the data (test) |
| Metric | L1 CD (bed) |
| Unit | SCALAR |
| Direction | Lower 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

- [L1 CD (bed)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(bed)>): Lower is better; unit: SCALAR.

- [L1 CD (bookcase)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(bookcase)>): Lower is better; unit: SCALAR.

- [L1 CD (desk)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(desk)>): Lower is better; unit: SCALAR.

- [L1 CD (misc)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(misc)>): Lower is better; unit: SCALAR.

- [L1 CD (sofa)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(sofa)>): Lower is better; unit: SCALAR.

- [L1 CD (table)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(table)>): Lower is better; unit: SCALAR.

- [L1 CD (tool)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(tool)>): Lower is better; unit: SCALAR.

- [L1 CD (wardrobe)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=L1%20CD%20(wardrobe)>): Lower is better; unit: SCALAR.

- [Average L1 CD](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md?metric=Average%20L1%20CD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | L1 CD (bed) | Result date | Report paper |
| --- | --- | --- | --- |
| MetaSSP | 0.0172 | Not recorded | 69896a23c97a0b3e3b5dc572 |
| SSMP | 0.0673 | Not recorded | 69896a23c97a0b3e3b5dc572 |
| 3D attributeflow | 0.0919 | Not recorded | 69896a23c97a0b3e3b5dc572 |
| Pix2Voxel | 0.0947 | Not recorded | 69896a23c97a0b3e3b5dc572 |
| Pixel2Point | 0.1116 | Not recorded | 69896a23c97a0b3e3b5dc572 |

### MetaSSP

L1 CD (bed): 0.0172. Result ID: 6997372f5698665ec4871121.

[Reporting paper](<https://www.sota2.com/research/paper/69896a23c97a0b3e3b5dc572.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69896a23c97a0b3e3b5dc572.md>)

Recorded evaluation configuration: {"Training Data":"10%"}. This record does not assert independent reproduction.

### SSMP

L1 CD (bed): 0.0673. Result ID: 6997372f5698665ec4871120.

[Reporting paper](<https://www.sota2.com/research/paper/69896a23c97a0b3e3b5dc572.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d31e209131cea6a10c.md>)

Recorded evaluation configuration: {"Training Data":"10%"}. This record does not assert independent reproduction.

### 3D attributeflow

L1 CD (bed): 0.0919. Result ID: 6997372f5698665ec487111d.

[Reporting paper](<https://www.sota2.com/research/paper/69896a23c97a0b3e3b5dc572.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320d6.md>)

[Implementation](<https://github.com/junshengzhou/3DAttriFlow>)

Recorded evaluation configuration: {"Training Data":"10%"}. This record does not assert independent reproduction.

### Pix2Voxel

L1 CD (bed): 0.0947. Result ID: 6997372f5698665ec487111f.

[Reporting paper](<https://www.sota2.com/research/paper/69896a23c97a0b3e3b5dc572.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ad1e209131cea17b89.md>)

[Implementation](<https://haozhexie.com/project/pix2vox>)

Recorded evaluation configuration: {"Training Data":"10%"}. This record does not assert independent reproduction.

### Pixel2Point

L1 CD (bed): 0.1116. Result ID: 6997372f5698665ec487111e.

[Reporting paper](<https://www.sota2.com/research/paper/69896a23c97a0b3e3b5dc572.md>)

Recorded evaluation configuration: {"Training Data":"10%"}. This record does not assert independent reproduction.

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