threedle/GeoCode
GeoCode maps 3D shapes to a human-interpretable parameter space, allowing to intuitively edit the recovered 3D shapes from a point cloud or sketch input.
This project helps 3D artists and designers create and modify intricate 3D shapes more easily. You can input a simple point cloud or a sketch, and it will generate a detailed 3D model that can be intuitively edited by adjusting human-interpretable parameters. This is ideal for anyone who designs or works with 3D models and needs a more accessible way to generate and refine complex shapes without extensive coding or node graph expertise.
412 stars. No commits in the last 6 months.
Use this if you need to quickly generate and adjust complex 3D shapes from basic inputs like sketches or point clouds, and want intuitive controls rather than deep technical knowledge of procedural programming.
Not ideal if you are solely looking for a general-purpose 3D modeling tool without the need for procedural generation or direct manipulation via high-level parameters.
Stars
412
Forks
22
Language
Python
License
—
Category
Last pushed
Mar 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/threedle/GeoCode"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.