ubc-vision/vivid123

[CVPR 2024 Highlight] ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models

36
/ 100
Emerging

This project helps 3D artists, game developers, or product designers create consistent 360-degree views of an object from just a single input image. You provide one picture of an object, and it generates a video showing that object from various new angles, maintaining a smooth appearance. This is ideal for quickly generating turnaround animations or diverse product shots.

179 stars. No commits in the last 6 months.

Use this if you need to generate multiple, consistent views of an object from a single image for presentations, virtual environments, or product showcases.

Not ideal if you need to reconstruct a 3D model with precise geometric accuracy, as this focuses on generating realistic video views rather than detailed mesh data.

3D art Product visualization Game asset creation Computer graphics Virtual photography
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

179

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Jul 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ubc-vision/vivid123"

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