DLR-RM/shape-completion
Code and Datasets for 3D Shape Completion related publications
This project helps robotics engineers and 3D vision researchers complete partially scanned or obscured 3D objects. By taking incomplete point clouds or depth images, it generates full, watertight 3D models. It's designed for professionals working with robotic perception, virtual reality, or generative AI who need accurate 3D representations from sparse data.
Use this if you need to reconstruct complete 3D shapes from partial scans, such as improving robotic grasping or creating realistic virtual environments from imperfect real-world data.
Not ideal if your primary need is for simple mesh reconstruction from clean, full point clouds or if you're not working with deep learning models for 3D data.
Stars
14
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DLR-RM/shape-completion"
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...