WHU-USI3DV/VistaDream
VistaDream reconstructs 3D scenes from single-view images using a training-free diffusion-based framework that samples multiview-consistent RGB and depth outputs.
Not currently ranked — collecting fresh signals.
star history
VistaDream is a PyTorch implementation for single-view 3D scene reconstruction. It employs a training-free approach leveraging diffusion models to generate multiview-consistent images and depth maps, enabling novel view synthesis from a single input image. The method produces high-quality RGB renderings and depth information for the reconstructed 3D scene without requiring additional training.
Frequently asked
- What is WHU-USI3DV/VistaDream?
- VistaDream reconstructs 3D scenes from single-view images using a training-free diffusion-based framework that samples multiview-consistent RGB and depth outputs.
- Is VistaDream open source?
- Yes — WHU-USI3DV/VistaDream is open source, released under the MIT license.
- What language is VistaDream written in?
- WHU-USI3DV/VistaDream is primarily written in Python.
- How popular is VistaDream?
- WHU-USI3DV/VistaDream has 538 stars on GitHub.
- Where can I find VistaDream?
- WHU-USI3DV/VistaDream is on GitHub at https://github.com/WHU-USI3DV/VistaDream.