# Image-to-Texture Generation on 3D-FRONT

Source: [Image-to-Texture Generation on 3D-FRONT](<https://www.sota2.com/research/sota/image-to-texture-generation-on-3d-front>)

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

Data updated: 2026-03-20T10:29:13.120Z

Evaluation of Image-to-Texture Generation performance on the 3D-FRONT dataset, utilizing metrics including CLIP-I, CLIP-FID, Q-Align IQA, and Q-Align IAA.

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-Texture Generation |
| Dataset (including any stated split) | 3D-FRONT |
| Metric | CLIP-I |
| Unit | SCALAR |
| Direction | Higher 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

- [CLIP-I](<https://www.sota2.com/research/sota/image-to-texture-generation-on-3d-front.md?metric=CLIP-I>): Higher is better; unit: SCALAR.

- [CLIP-FID](<https://www.sota2.com/research/sota/image-to-texture-generation-on-3d-front.md?metric=CLIP-FID>): Lower is better; unit: SCALAR.

- [Q-Align IQA](<https://www.sota2.com/research/sota/image-to-texture-generation-on-3d-front.md?metric=Q-Align%20IQA>): Higher is better; unit: SCALAR.

- [Q-Align IAA](<https://www.sota2.com/research/sota/image-to-texture-generation-on-3d-front.md?metric=Q-Align%20IAA>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CLIP-I | Result date | Report paper |
| --- | --- | --- | --- |
| CustomTex | 0.797 | Not recorded | 69bcd4af0636e5bf4afc2c51 |
| SceneTex-IPA | 0.741 | Not recorded | 69bcd4af0636e5bf4afc2c51 |
| Paint3D | 0.694 | Not recorded | 69bcd4af0636e5bf4afc2c51 |
| HY3D-2.1 | 0.682 | Not recorded | 69bcd4af0636e5bf4afc2c51 |

### CustomTex

CLIP-I: 0.797. Result ID: 69bd215c47f34ce924a7f36c.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4af0636e5bf4afc2c51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bcd4af0636e5bf4afc2c51.md>)

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

### SceneTex-IPA

CLIP-I: 0.741. Result ID: 69bd215c47f34ce924a7f36b.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4af0636e5bf4afc2c51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71471e209131cea505ba.md>)

[Implementation](<https://daveredrum.github.io/SceneTex/>)

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

### Paint3D

CLIP-I: 0.694. Result ID: 69bd215c47f34ce924a7f369.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4af0636e5bf4afc2c51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a71e209131cea52592.md>)

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

### HY3D-2.1

CLIP-I: 0.682. Result ID: 69bd215c47f34ce924a7f36a.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4af0636e5bf4afc2c51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79801e209131cea7dd57.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.