Drexubery/ViewCrafter
ViewCrafter is a video diffusion model that generates high-fidelity novel views from single or sparse reference images.
Not currently ranked — collecting fresh signals.
star history
ViewCrafter is a video diffusion model designed for high-fidelity novel view synthesis, generating new viewpoints from a single or sparse reference image. It leverages a pre-trained video diffusion model and supports precise pose control for controlled viewpoint generation. The project includes pre-trained models, evaluation scripts, and sparse-view synthesis capabilities, and was published at IEEE TPAMI 2025.
Frequently asked
- What is Drexubery/ViewCrafter?
- ViewCrafter is a video diffusion model that generates high-fidelity novel views from single or sparse reference images.
- Is ViewCrafter open source?
- Yes — Drexubery/ViewCrafter is open source, released under the Apache-2.0 license.
- What language is ViewCrafter written in?
- Drexubery/ViewCrafter is primarily written in Python.
- How popular is ViewCrafter?
- Drexubery/ViewCrafter has 1.6k stars on GitHub.
- Where can I find ViewCrafter?
- Drexubery/ViewCrafter is on GitHub at https://github.com/Drexubery/ViewCrafter.