# 3D Reconstruction on In-house Real X-ray Dataset (test)

Source: [3D Reconstruction on In-house Real X-ray Dataset (test)](<https://www.sota2.com/research/sota/3d-reconstruction-on-in-house-real-x-ray-dataset-test>)

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

Data updated: 2026-02-26T06:03:19.864Z

Evaluation of 3D Reconstruction performance on the test split of the In-house Real X-ray Dataset, measured using SSIM and PSNR.

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) | In-house Real X-ray Dataset (test) |
| Metric | SSIM |
| Unit | SCALAR |
| 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

- [SSIM](<https://www.sota2.com/research/sota/3d-reconstruction-on-in-house-real-x-ray-dataset-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR (dB)](<https://www.sota2.com/research/sota/3d-reconstruction-on-in-house-real-x-ray-dataset-test.md?metric=PSNR%20(dB)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | SSIM | Result date | Report paper |
| --- | --- | --- | --- |
| RadGS-Reg | 0.9451 | Not recorded | 68fa7af01e209131cea85df8 |
| SAX-NeRF | 0.5723 | Not recorded | 68fa7af01e209131cea85df8 |
| R2-GS | 0.5236 | Not recorded | 68fa7af01e209131cea85df8 |
| 3DGR | 0.3993 | Not recorded | 68fa7af01e209131cea85df8 |
| DiffVox | 0.1548 | Not recorded | 68fa7af01e209131cea85df8 |

### RadGS-Reg

SSIM: 0.9451. Result ID: 698b7f467a967eddb76f1572.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85df8.md>)

[Implementation](<https://www.sota2.com/github.com/shenao1995/RadGS_Reg>)

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

### SAX-NeRF

SSIM: 0.5723. Result ID: 698b7f467a967eddb76f156f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a31e209131cea57b77.md>)

[Implementation](<https://github.com/caiyuanhao1998/SAX-NeRF>)

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

### R2-GS

SSIM: 0.5236. Result ID: 698b7f467a967eddb76f1571.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e07.md>)

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

### 3DGR

SSIM: 0.3993. Result ID: 698b7f467a967eddb76f1570.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75081e209131cea6564e.md>)

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

### DiffVox

SSIM: 0.1548. Result ID: 698b7f467a967eddb76f156e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85df8.md>)

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

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