# Unconditional Volumetric Synthesis on TaviCT (train)

Source: [Unconditional Volumetric Synthesis on TaviCT (train)](<https://www.sota2.com/research/sota/unconditional-volumetric-synthesis-on-tavict-train>)

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

Data updated: 2026-03-27T12:58:33.120Z

Evaluation of Unconditional Volumetric Synthesis performance on the TaviCT dataset (training split), measured using metrics such as FID, Precision, Recall, Density, Coverage, 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 | Unconditional Volumetric Synthesis |
| Dataset (including any stated split) | TaviCT (train) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/unconditional-volumetric-synthesis-on-tavict-train.md?metric=FID>): Lower is better; unit: SCALAR.

- [Precision (P)](<https://www.sota2.com/research/sota/unconditional-volumetric-synthesis-on-tavict-train.md?metric=Precision%20(P)>): Higher is better; unit: SCALAR.

- [Recall (R)](<https://www.sota2.com/research/sota/unconditional-volumetric-synthesis-on-tavict-train.md?metric=Recall%20(R)>): Higher is better; unit: SCALAR.

- [Density (D)](<https://www.sota2.com/research/sota/unconditional-volumetric-synthesis-on-tavict-train.md?metric=Density%20(D)>): Higher is better; unit: SCALAR.

- [Coverage (C)](<https://www.sota2.com/research/sota/unconditional-volumetric-synthesis-on-tavict-train.md?metric=Coverage%20(C)>): Higher is better; unit: SCALAR.

- [MS-SSIM](<https://www.sota2.com/research/sota/unconditional-volumetric-synthesis-on-tavict-train.md?metric=MS-SSIM>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Real train | 3.1 | Not recorded | 69c60eff0636e5bf4afc84e0 |
| VolDiT | 21.4 | Not recorded | 69c60eff0636e5bf4afc84e0 |
| U-Net LDM | 36.8 | Not recorded | 69c60eff0636e5bf4afc84e0 |
| HA-GAN | 155.5 | Not recorded | 69c60eff0636e5bf4afc84e0 |

### Real train

FID: 3.1. Result ID: 69c67e4b47f34ce924b072b3.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e0.md>)

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

### VolDiT

FID: 21.4. Result ID: 69c67e4b47f34ce924b072b6.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e0.md>)

Recorded evaluation configuration: {"Capacity":"L","Patch size":"2"}. This record does not assert independent reproduction.

### U-Net LDM

FID: 36.8. Result ID: 69c67e4b47f34ce924b072b4.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7acd1e209131cea852f7.md>)

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

### HA-GAN

FID: 155.5. Result ID: 69c67e4b47f34ce924b072b5.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e0.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.
