# Image-to-Image Translation on CelebA-HQ gender as class (test)

Source: [Image-to-Image Translation on CelebA-HQ gender as class (test)](<https://www.sota2.com/research/sota/image-to-image-translation-on-celeba-hq-gender-as-class-test>)

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

Data updated: 2026-02-26T06:05:51.416Z

Evaluation of Image-to-Image Translation models focusing on gender attribute translation (as class) on the test split of the CelebA-HQ dataset, measured using TC and FID.

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 | Image-to-Image Translation |
| Dataset (including any stated split) | CelebA-HQ gender as class (test) |
| Metric | TC |
| Unit | SCALAR |
| Direction | Lower 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

- [TC](<https://www.sota2.com/research/sota/image-to-image-translation-on-celeba-hq-gender-as-class-test.md?metric=TC>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/image-to-image-translation-on-celeba-hq-gender-as-class-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [FID (Unconditional)](<https://www.sota2.com/research/sota/image-to-image-translation-on-celeba-hq-gender-as-class-test.md?metric=FID%20(Unconditional)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | TC | Result date | Report paper |
| --- | --- | --- | --- |
| 3D-aware I2I translation | 3.743 | Not recorded | 68fa6ede1e209131cea427e8 |
| StarGANv2 | 10.25 | Not recorded | 68fa6ede1e209131cea427e8 |
| Kunhee et al. | 10.462 | Not recorded | 68fa6ede1e209131cea427e8 |
| Liu et al. | 13.315 | Not recorded | 68fa6ede1e209131cea427e8 |
| MUNIT | 30.24 | Not recorded | 68fa6ede1e209131cea427e8 |
| MSGAN | 31.641 | Not recorded | 68fa6ede1e209131cea427e8 |
| DRIT | 35.452 | Not recorded | 68fa6ede1e209131cea427e8 |

### 3D-aware I2I translation

TC: 3.743. Result ID: 69904fbc3a6c314849ffa2e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

Recorded evaluation configuration: {"mode":"Ours (3D)"}. This record does not assert independent reproduction.

### StarGANv2

TC: 10.25. Result ID: 69904fbc3a6c314849ffa2e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603b.md>)

[Implementation](<https://github.com/clovaai/stargan-v2>)

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

### Kunhee et al.

TC: 10.462. Result ID: 69904fbc3a6c314849ffa2e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea3210e.md>)

Recorded evaluation configuration: {"model\_source":"pre-trained networks provided by authors"}. This record does not assert independent reproduction.

### Liu et al.

TC: 13.315. Result ID: 69904fbc3a6c314849ffa2e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265f4.md>)

Recorded evaluation configuration: {"model\_source":"pre-trained networks provided by authors"}. This record does not assert independent reproduction.

### MUNIT

TC: 30.24. Result ID: 69904fbc3a6c314849ffa2e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c01e209131cea06469.md>)

[Implementation](<https://github.com/nvlabs/MUNIT>)

Recorded evaluation configuration: {"source\_of\_results":"StarGANv2"}. This record does not assert independent reproduction.

### MSGAN

TC: 31.641. Result ID: 69904fbc3a6c314849ffa2e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ba1e209131cea18255.md>)

[Implementation](<https://github.com/akanimax/msg-stylegan-tf>)

Recorded evaluation configuration: {"source\_of\_results":"StarGANv2"}. This record does not assert independent reproduction.

### DRIT

TC: 35.452. Result ID: 69904fbc3a6c314849ffa2e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea427e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64aa1e209131cea05f9e.md>)

[Implementation](<https://github.com/HsinYingLee/DRIT/>)

Recorded evaluation configuration: {"source\_of\_results":"StarGANv2"}. This record does not assert independent reproduction.

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