# 3D CT Reconstruction on Synthetic CT datasets (engine, foot, jaw, pepper, teapot) P50 noise level

Source: [3D CT Reconstruction on Synthetic CT datasets (engine, foot, jaw, pepper, teapot) P50 noise level](<https://www.sota2.com/research/sota/3d-ct-reconstruction-on-synthetic-ct-datasets-engine-foot-jaw-pepper-teapot-p50-noise-level>)

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

Data updated: 2026-03-04T17:01:33.173Z

Evaluation of 3D CT Reconstruction performance on a synthetic dataset comprising engine, foot, jaw, pepper, and teapot phantoms, tested at P50 noise level, typically measured using PSNR and MS-SSIM.

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 CT Reconstruction |
| Dataset (including any stated split) | Synthetic CT datasets (engine, foot, jaw, pepper, teapot) P50 noise level |
| Metric | MS-SSIM (2D) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [MS-SSIM (2D)](<https://www.sota2.com/research/sota/3d-ct-reconstruction-on-synthetic-ct-datasets-engine-foot-jaw-pepper-teapot-p50-noise-level.md?metric=MS-SSIM%20(2D)>): Higher is better; unit: SCALAR.

- [PSNR (3D)](<https://www.sota2.com/research/sota/3d-ct-reconstruction-on-synthetic-ct-datasets-engine-foot-jaw-pepper-teapot-p50-noise-level.md?metric=PSNR%20(3D)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | MS-SSIM (2D) | Result date | Report paper |
| --- | --- | --- | --- |
| 3D FoJ | 0.754 | Not recorded | 69a66c582d603e6de3e3d179 |
| 3D-TV | 0.703 | Not recorded | 69a66c582d603e6de3e3d179 |
| Filter2Noise | 0.663 | Not recorded | 69a66c582d603e6de3e3d179 |
| R2-Gaussian | 0.574 | Not recorded | 69a66c582d603e6de3e3d179 |

### 3D FoJ

MS-SSIM (2D): 0.754. Result ID: 69a8655e6dbb7075b950186e.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c582d603e6de3e3d179.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c582d603e6de3e3d179.md>)

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

### 3D-TV

MS-SSIM (2D): 0.703. Result ID: 69a8655e6dbb7075b950186b.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c582d603e6de3e3d179.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa54751e209131ce98bc03.md>)

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

### Filter2Noise

MS-SSIM (2D): 0.663. Result ID: 69a8655e6dbb7075b950186d.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c582d603e6de3e3d179.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa781f1e209131cea76df6.md>)

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

### R2-Gaussian

MS-SSIM (2D): 0.574. Result ID: 69a8655e6dbb7075b950186c.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c582d603e6de3e3d179.md>)

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