# 3D Reconstruction on Synthetic Cell Structures (test)

Source: [3D Reconstruction on Synthetic Cell Structures (test)](<https://www.sota2.com/research/sota/3d-reconstruction-on-synthetic-cell-structures-test>)

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

Data updated: 2026-02-26T05:21:09.790Z

Evaluation of 3D Reconstruction performance on the test split of the Synthetic Cell Structures dataset, reporting image quality metrics like 2D/3D PSNR, MSE, and DSSIM.

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) | Synthetic Cell Structures (test) |
| Metric | 2D 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

- [2D PSNR](<https://www.sota2.com/research/sota/3d-reconstruction-on-synthetic-cell-structures-test.md?metric=2D%20PSNR>): Higher is better; unit: SCALAR.

- [2D MSE](<https://www.sota2.com/research/sota/3d-reconstruction-on-synthetic-cell-structures-test.md?metric=2D%20MSE>): Lower is better; unit: SCALAR.

- [2D DSSIM](<https://www.sota2.com/research/sota/3d-reconstruction-on-synthetic-cell-structures-test.md?metric=2D%20DSSIM>): Higher is better; unit: SCALAR.

- [3D PSNR](<https://www.sota2.com/research/sota/3d-reconstruction-on-synthetic-cell-structures-test.md?metric=3D%20PSNR>): Higher is better; unit: SCALAR.

- [3D MSE](<https://www.sota2.com/research/sota/3d-reconstruction-on-synthetic-cell-structures-test.md?metric=3D%20MSE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | 2D PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| L2Clean | 20.73 | Not recorded | 68fa6c171e209131cea32120 |
| OursSup | 20.07 | Not recorded | 68fa6c171e209131cea32120 |
| Ours | 19.93 | Not recorded | 68fa6c171e209131cea32120 |
| L2Den | 18.15 | Not recorded | 68fa6c171e209131cea32120 |
| L2Noisy | 13.86 | Not recorded | 68fa6c171e209131cea32120 |
| SIRT | 3.27 | Not recorded | 68fa6c171e209131cea32120 |
| WBP | 2.97 | Not recorded | 68fa6c171e209131cea32120 |

### L2Clean

2D PSNR: 20.73. Result ID: 698ece11ffc3901de0a16711.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68171e209131cea1a247.md>)

Recorded evaluation configuration: {"Loss":"L2","Implicit Representation":true,"Access to Clean GT":true}. This record does not assert independent reproduction.

### OursSup

2D PSNR: 20.07. Result ID: 698ece11ffc3901de0a16710.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

[Implementation](<https://github.com/HannahKniesel/Implicit-Electron-Tomography.git>)

Recorded evaluation configuration: {"Loss":"LMLE","Implicit Representation":true,"Access to Clean GT":true}. This record does not assert independent reproduction.

### Ours

2D PSNR: 19.93. Result ID: 698ece11ffc3901de0a1670f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

[Implementation](<https://github.com/HannahKniesel/Implicit-Electron-Tomography.git>)

Recorded evaluation configuration: {"Loss":"LMLE","Implicit Representation":true,"Access to Clean GT":false}. This record does not assert independent reproduction.

### L2Den

2D PSNR: 18.15. Result ID: 698ece11ffc3901de0a1670e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

Recorded evaluation configuration: {"Loss":"L2","Implicit Representation":true,"Access to Clean GT":false}. This record does not assert independent reproduction.

### L2Noisy

2D PSNR: 13.86. Result ID: 698ece11ffc3901de0a1670d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68171e209131cea1a247.md>)

Recorded evaluation configuration: {"Loss":"L2","Implicit Representation":false,"Access to Clean GT":false}. This record does not assert independent reproduction.

### SIRT

2D PSNR: 3.27. Result ID: 698ece11ffc3901de0a1670c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

Recorded evaluation configuration: {"Loss":"L2","Implicit Representation":false,"Access to Clean GT":false}. This record does not assert independent reproduction.

### WBP

2D PSNR: 2.97. Result ID: 698ece11ffc3901de0a1670b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c171e209131cea32120.md>)

Recorded evaluation configuration: {"Loss":"L2","Implicit Representation":false,"Access to Clean GT":false}. This record does not assert independent reproduction.

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