# Single Image to 3D Reconstruction on Google Scanned Objects (GSO) orbiting views

Source: [Single Image to 3D Reconstruction on Google Scanned Objects (GSO) orbiting views](<https://www.sota2.com/research/sota/single-image-to-3d-reconstruction-on-google-scanned-objects-gso-orbiting-views>)

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

Data updated: 2026-02-26T05:56:14.283Z

Evaluation of Single Image to 3D Reconstruction performance on the orbiting views subset of the Google Scanned Objects (GSO) dataset, reporting image fidelity metrics such as PSNR, SSIM, and LPIPS.

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 | Single Image to 3D Reconstruction |
| Dataset (including any stated split) | Google Scanned Objects (GSO) orbiting views |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [PSNR](<https://www.sota2.com/research/sota/single-image-to-3d-reconstruction-on-google-scanned-objects-gso-orbiting-views.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/single-image-to-3d-reconstruction-on-google-scanned-objects-gso-orbiting-views.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/single-image-to-3d-reconstruction-on-google-scanned-objects-gso-orbiting-views.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| MVBoost | 18.561 | Not recorded | 68fa76021e209131cea6ae5e |
| CRM | 17.435 | Not recorded | 68fa76021e209131cea6ae5e |
| VFusion3D | 17.416 | Not recorded | 68fa76021e209131cea6ae5e |
| LGM | 17.148 | Not recorded | 68fa76021e209131cea6ae5e |
| InstantMesh | 16.796 | Not recorded | 68fa76021e209131cea6ae5e |
| OpenLRM | 16.728 | Not recorded | 68fa76021e209131cea6ae5e |
| TriplaneGaussian | 13.702 | Not recorded | 68fa76021e209131cea6ae5e |

### MVBoost

PSNR: 18.561. Result ID: 699420773a6c3148491b3e89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Implementation](<https://github.com/Piggy-ch/MVBoost>)

Recorded evaluation configuration: {"Representation":"3D Gaussian Splatting"}. This record does not assert independent reproduction.

### CRM

PSNR: 17.435. Result ID: 699420773a6c3148491b3e85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727b1e209131cea56ad8.md>)

Recorded evaluation configuration: {"Representation":"Mesh"}. This record does not assert independent reproduction.

### VFusion3D

PSNR: 17.416. Result ID: 699420773a6c3148491b3e84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74321e209131cea605a6.md>)

Recorded evaluation configuration: {"Representation":"NeRF"}. This record does not assert independent reproduction.

### LGM

PSNR: 17.148. Result ID: 699420773a6c3148491b3e88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72291e209131cea54dd3.md>)

Recorded evaluation configuration: {"Representation":"3D Gaussian Splatting"}. This record does not assert independent reproduction.

### InstantMesh

PSNR: 16.796. Result ID: 699420773a6c3148491b3e86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72da1e209131cea58e96.md>)

Recorded evaluation configuration: {"Representation":"Mesh"}. This record does not assert independent reproduction.

### OpenLRM

PSNR: 16.728. Result ID: 699420773a6c3148491b3e83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72721e209131cea565c0.md>)

Recorded evaluation configuration: {"Representation":"NeRF"}. This record does not assert independent reproduction.

### TriplaneGaussian

PSNR: 13.702. Result ID: 699420773a6c3148491b3e87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76021e209131cea6ae5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa718c1e209131cea51ee7.md>)

[Implementation](<https://zouzx.github.io/TriplaneGaussian/>)

Recorded evaluation configuration: {"Representation":"3D Gaussian Splatting"}. This record does not assert independent reproduction.

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