raphaelsulzer/dgnn
[SGP 2021] Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
This project helps create detailed 3D models from raw 3D scan data, which often contains only scattered points. It takes in point clouds—essentially a collection of 3D coordinates representing an object's surface—and outputs a clean, continuous 3D mesh. This is ideal for 3D artists, computer graphics professionals, and researchers working with scanned objects or environments who need a complete digital surface.
No commits in the last 6 months.
Use this if you need to reliably convert noisy or incomplete 3D point cloud data into a smooth, high-quality 3D surface mesh for visualization, analysis, or further processing.
Not ideal if you're looking for a simple click-and-drag 3D modeling software, as this tool requires some technical setup and command-line execution.
Stars
42
Forks
5
Language
Python
License
MIT
Category
Last pushed
Mar 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/raphaelsulzer/dgnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openspyrit/spyrit
A Python toolbox for deep image reconstruction, with emphasis on single-pixel imaging.
RobotLocomotion/pytorch-dense-correspondence
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"
Fyusion/LLFF
Code release for Local Light Field Fusion at SIGGRAPH 2019
pmh47/dirt
DIRT: a fast differentiable renderer for TensorFlow
marrlab/SHAPR_torch
SHAPR: Code for "Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D...