WHU-USI3DV/VistaDream

[ICCV 2025] VistaDream: Sampling multiview consistent images for single-view scene reconstruction

40
/ 100
Emerging

This project helps you reconstruct a high-quality 3D scene from just a single photograph or a few sparse images. You provide an input image, and it generates multiple consistent views and depth maps, effectively building a virtual 3D representation of the scene. This is ideal for 3D artists, game developers, or architects looking to quickly create 3D models from existing images.

528 stars. No commits in the last 6 months.

Use this if you need to generate a realistic 3D scene from a single 2D image without extensive manual modeling or photography.

Not ideal if you require highly precise, measured 3D models for engineering or manufacturing, as this focuses on visual consistency rather than exact geometric accuracy.

3D-reconstruction virtual-environment-creation CGI architectural-visualization game-asset-generation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

528

Forks

25

Language

Python

License

MIT

Last pushed

Jul 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WHU-USI3DV/VistaDream"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.