byeongjun-park/HarmonyView

[CVPR 2024] Official pytorch implementation of "HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D"

39
/ 100
Emerging

This project helps 3D artists, designers, or product developers create detailed 3D models from just a single 2D image. You input one picture of an object, and it generates a set of consistent and diverse views, which can then be used to reconstruct a full 3D mesh. This is ideal for anyone needing to quickly turn a 2D reference into a usable 3D asset.

132 stars. No commits in the last 6 months.

Use this if you need to generate multiple realistic views and a 3D model of an object from a single photograph, especially for product visualization or virtual content creation.

Not ideal if you already have multiple views or a full 3D scan of an object, or if you require extremely precise, measurable CAD models for engineering.

3D-modeling product-design virtual-asset-creation digital-art computer-graphics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

132

Forks

12

Language

Python

License

MIT

Last pushed

Mar 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/byeongjun-park/HarmonyView"

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