# Image-driven 3D Scene Editing on Image-driven editing set 5 scenes (test)

Source: [Image-driven 3D Scene Editing on Image-driven editing set 5 scenes (test)](<https://www.sota2.com/research/sota/image-driven-3d-scene-editing-on-image-driven-editing-set-5-scenes-test>)

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

Data updated: 2026-02-26T05:38:27.968Z

Evaluation of Image-driven 3D Scene Editing performance on the test split of the Image-driven editing set 5 scenes, measured using CLIP direction similarity, DINO similarity, and Vote Percentage.

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-driven 3D Scene Editing |
| Dataset (including any stated split) | Image-driven editing set 5 scenes (test) |
| Metric | CLIP Direction Similarity |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 Direction Similarity](<https://www.sota2.com/research/sota/image-driven-3d-scene-editing-on-image-driven-editing-set-5-scenes-test.md?metric=CLIP%20Direction%20Similarity>): Higher is better; unit: PERCENT.

- [DINO Similarity](<https://www.sota2.com/research/sota/image-driven-3d-scene-editing-on-image-driven-editing-set-5-scenes-test.md?metric=DINO%20Similarity>): Higher is better; unit: PERCENT.

- [Vote Percentage](<https://www.sota2.com/research/sota/image-driven-3d-scene-editing-on-image-driven-editing-set-5-scenes-test.md?metric=Vote%20Percentage>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CLIP Direction Similarity | Result date | Report paper |
| --- | --- | --- | --- |
| CustomNeRF | 20.07 | Not recorded | 68fa71571e209131cea50aa4 |
| RePaint-NeRF\* | 16.46 | Not recorded | 68fa71571e209131cea50aa4 |
| CustomNeRF | 15.47 | Not recorded | 68fa71571e209131cea50aa4 |

### CustomNeRF

CLIP Direction Similarity: 20.07. Result ID: 6991c66c3a6c3148490a832f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50aa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50aa4.md>)

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

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

### RePaint-NeRF\*

CLIP Direction Similarity: 16.46. Result ID: 6991c66c3a6c3148490a832e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50aa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71661e209131cea51303.md>)

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

### CustomNeRF

CLIP Direction Similarity: 15.47. Result ID: 6991c66c3a6c3148490a832d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50aa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50aa4.md>)

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

Recorded evaluation configuration: {"Splicing Loss":true}. This record does not assert independent reproduction.

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