OVIE
OVIE generates a view of a scene from an input image and a target camera pose. It predicts the new image without building a separate scene representation for each input.
Research release
The checkpoint has a specific training history
The base model learns from unpaired images in the wild using generated view pairs. Its published base setup uses 256-by-256 images.ovie: Kyutai model card
Generated views are estimates
Practical guidance. A plausible new view does not establish the true shape of hidden objects. Check consistency when using generated views for a larger scene or animation.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/ovie |
| License | MIT.ovie: Kyutai model card |
Related models
An OVIE model retrained at 512-by-512 resolution for single-image novel-view generation.
Launch date not confirmedResearch releaseDownloadable- OVIE DL3DV
Kyutai · OVIE
An OVIE novel-view model fine-tuned for 50,000 steps on paired DL3DV multi-view data.
Launch date not confirmedResearch releaseDownloadable - OVIE RealEstate10K
Kyutai · OVIE
An OVIE novel-view model fine-tuned for 50,000 steps on paired RealEstate10K indoor scenes.
Launch date not confirmedResearch releaseDownloadable