mabaorui/NeuralPull
Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
This project helps reconstruct detailed 3D surfaces from raw scan data, specifically point clouds or even single 2D images. You input noisy point cloud data or an image of an object, and it outputs a clean, continuous 3D model (a mesh). This is ideal for researchers and practitioners working with 3D data in fields like computer graphics, robotics, and augmented reality.
175 stars. No commits in the last 6 months.
Use this if you need to transform sparse 3D scan data or a 2D image into an accurate, complete 3D surface model.
Not ideal if you are looking for a simple, off-the-shelf 3D modeling application for end-users without technical expertise.
Stars
175
Forks
23
Language
Python
License
MIT
Category
Last pushed
Jun 03, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mabaorui/NeuralPull"
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...