shubhtuls/volumetricPrimitives
Code release for "Learning Shape Abstractions by Assembling Volumetric Primitives " (CVPR 2017)
This project helps researchers in computer vision and graphics analyze 3D shapes by breaking them down into simpler, volumetric building blocks like cubes. It takes a detailed 3D model, such as a scanned object or CAD design, and outputs a representation of that object as a collection of basic 3D primitives. Academics and practitioners in fields like 3D scene understanding or robotic perception would use this to simplify complex shapes for further analysis.
163 stars. No commits in the last 6 months.
Use this if you need to represent complex 3D objects with a simplified set of basic volumetric shapes, rather than a dense mesh or point cloud.
Not ideal if you require a highly detailed or exact geometric representation of a 3D object for tasks like precision engineering or photorealistic rendering.
Stars
163
Forks
34
Language
Lua
License
—
Category
Last pushed
Jan 04, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/shubhtuls/volumetricPrimitives"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.