byeongjun-park/HarmonyView
[CVPR 2024] Official pytorch implementation of "HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D"
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.
Stars
132
Forks
12
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...