# Cross-modal Image Translation on IXI T2-\>T1

Source: [Cross-modal Image Translation on IXI T2-\>T1](<https://www.sota2.com/research/sota/cross-modal-image-translation-on-ixi-t2-t1>)

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

Data updated: 2026-02-26T06:03:25.675Z

Evaluation of cross-modal image translation performance translating from the T2 modality to the T1 modality using the IXI dataset, assessed using metrics like SSIM, PSNR, MSE, and MAE.

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 | Cross-modal Image Translation |
| Dataset (including any stated split) | IXI T2→T1 |
| Metric | SSIM |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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/cross-modal-image-translation-on-ixi-t2-t1.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/cross-modal-image-translation-on-ixi-t2-t1.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [MSE](<https://www.sota2.com/research/sota/cross-modal-image-translation-on-ixi-t2-t1.md?metric=MSE>): Lower is better; unit: SCALAR.

- [MAE](<https://www.sota2.com/research/sota/cross-modal-image-translation-on-ixi-t2-t1.md?metric=MAE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | SSIM | Result date | Report paper |
| --- | --- | --- | --- |
| CDTSDE | 0.82 | Not recorded | 69784714a2b28e761d87c992 |
| DOSSR | 0.8 | Not recorded | 69784714a2b28e761d87c992 |
| Pix2Pix | 0.71 | Not recorded | 69784714a2b28e761d87c992 |
| ABridge | 0.35 | Not recorded | 69784714a2b28e761d87c992 |
| DBIM | 0.33 | Not recorded | 69784714a2b28e761d87c992 |
| BBDM | 0.01 | Not recorded | 69784714a2b28e761d87c992 |

### CDTSDE

SSIM: 0.82. Result ID: 69978bbf5698665ec4e0d1ab.

[Reporting paper](<https://www.sota2.com/research/paper/69784714a2b28e761d87c992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69784714a2b28e761d87c992.md>)

Recorded evaluation configuration: {"Training steps":"10,000"}. This record does not assert independent reproduction.

### DOSSR

SSIM: 0.8. Result ID: 69978bbf5698665ec4e0d1a8.

[Reporting paper](<https://www.sota2.com/research/paper/69784714a2b28e761d87c992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bb7d.md>)

[Implementation](<https://github.com/AMD-AIG-AIMA/DoSSR>)

Recorded evaluation configuration: {"Training steps":"10,000"}. This record does not assert independent reproduction.

### Pix2Pix

SSIM: 0.71. Result ID: 69978bbf5698665ec4e0d1a6.

[Reporting paper](<https://www.sota2.com/research/paper/69784714a2b28e761d87c992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65151e209131cea0821e.md>)

[Implementation](<https://github.com/phillipi/pix2pix>)

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

### ABridge

SSIM: 0.35. Result ID: 69978bbf5698665ec4e0d1a7.

[Reporting paper](<https://www.sota2.com/research/paper/69784714a2b28e761d87c992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9953fdd5c36173db48.md>)

Recorded evaluation configuration: {"Training steps":"10,000"}. This record does not assert independent reproduction.

### DBIM

SSIM: 0.33. Result ID: 69978bbf5698665ec4e0d1aa.

[Reporting paper](<https://www.sota2.com/research/paper/69784714a2b28e761d87c992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa785a1e209131cea77ed5.md>)

Recorded evaluation configuration: {"Training steps":"10,000"}. This record does not assert independent reproduction.

### BBDM

SSIM: 0.01. Result ID: 69978bbf5698665ec4e0d1a9.

[Reporting paper](<https://www.sota2.com/research/paper/69784714a2b28e761d87c992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ece1e209131cea4243f.md>)

[Implementation](<https://github.com/xuekt98/BBDM>)

Recorded evaluation configuration: {"Training steps":"10,000","Sampling steps":1000}. This record does not assert independent reproduction.

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