henzler/platonicgan
Escaping Plato’s Cave: 3D Shape from Adversarial Rendering [ICCV 2019]
This project helps researchers and artists create 3D models from a collection of 2D images. You provide various 2D photos of an object or scene, and it generates a unique 3D shape that best represents them. It's ideal for anyone working with 3D reconstruction, computer vision, or digital content creation.
No commits in the last 6 months.
Use this if you need to generate a 3D model of an object or scene when you only have a collection of diverse 2D images.
Not ideal if you need precise measurements or a highly detailed 3D model from limited or very similar input images.
Stars
44
Forks
11
Language
Python
License
—
Category
Last pushed
Jun 10, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/henzler/platonicgan"
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.