# Image Synthesis on MureCom

Source: [Image Synthesis on MureCom](<https://www.sota2.com/research/sota/image-synthesis-on-murecom>)

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

Data updated: 2026-04-16T08:14:12.573Z

Evaluation of Image Synthesis models on the MureCom dataset, utilizing metrics such as CLIP-I, DINO, LPIPS, and 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 | Image Synthesis |
| Dataset (including any stated split) | MureCom |
| Metric | CLIP-I |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [CLIP-I](<https://www.sota2.com/research/sota/image-synthesis-on-murecom.md?metric=CLIP-I>): Higher is better; unit: SCALAR.

- [DINO Score](<https://www.sota2.com/research/sota/image-synthesis-on-murecom.md?metric=DINO%20Score>): Higher is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/image-synthesis-on-murecom.md?metric=LPIPS>): Lower is better; unit: SCALAR.

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

## Recorded results

| Method | CLIP-I | Result date | Report paper |
| --- | --- | --- | --- |
| PostureObjectstitch | 0.8143 | Not recorded | 69e06d057d0172140ec7ca24 |
| MureObjectStitch | 0.8139 | Not recorded | 69e06d057d0172140ec7ca24 |
| Anydoor | 0.8118 | Not recorded | 69e06d057d0172140ec7ca24 |
| ObjectStitch | 0.7891 | Not recorded | 69e06d057d0172140ec7ca24 |
| IC-Custom | 0.7891 | Not recorded | 69e06d057d0172140ec7ca24 |

### PostureObjectstitch

CLIP-I: 0.8143. Result ID: 69e09a5347f34ce924c9c199.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d057d0172140ec7ca24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06d057d0172140ec7ca24.md>)

Recorded evaluation configuration: {"Training Paradigm":"fine-tuning-based"}. This record does not assert independent reproduction.

### MureObjectStitch

CLIP-I: 0.8139. Result ID: 69e09a5347f34ce924c9c196.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d057d0172140ec7ca24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751cc.md>)

Recorded evaluation configuration: {"Training Paradigm":"fine-tuning-based"}. This record does not assert independent reproduction.

### Anydoor

CLIP-I: 0.8118. Result ID: 69e09a5347f34ce924c9c197.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d057d0172140ec7ca24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732a1e209131cea5adb6.md>)

Recorded evaluation configuration: {"Training Paradigm":"pre-trained"}. This record does not assert independent reproduction.

### ObjectStitch

CLIP-I: 0.7891. Result ID: 69e09a5347f34ce924c9c195.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d057d0172140ec7ca24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e1b1e209131cea3dd5a.md>)

Recorded evaluation configuration: {"Training Paradigm":"pre-trained"}. This record does not assert independent reproduction.

### IC-Custom

CLIP-I: 0.7891. Result ID: 69e09a5347f34ce924c9c198.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d057d0172140ec7ca24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a2e8.md>)

Recorded evaluation configuration: {"Training Paradigm":"pre-trained"}. This record does not assert independent reproduction.

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