https://github.com/zackakil/spatialy-aware-deep-learning
Project for building a deep net that can predict a 3D scene based on a 2D image.
https://github.com/zackakil/spatialy-aware-deep-learning
3d deep-learning machine-learning spatial tensorflow unity
Last synced: about 2 months ago
JSON representation
Project for building a deep net that can predict a 3D scene based on a 2D image.
- Host: GitHub
- URL: https://github.com/zackakil/spatialy-aware-deep-learning
- Owner: ZackAkil
- Created: 2018-08-31T14:20:04.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2018-09-13T19:24:45.000Z (almost 8 years ago)
- Last Synced: 2025-03-01T08:02:36.559Z (over 1 year ago)
- Topics: 3d, deep-learning, machine-learning, spatial, tensorflow, unity
- Language: C#
- Size: 285 KB
- Stars: 2
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# spatialy-aware-deep-learning
Project for building a deep net that can predict a 3D scene based on a 2D image.
- [ ] Build unity scen generator (start with just a box)
- [ ] Extract images from unity scene
- [ ] Feed images as input data
- [ ] Come up with way of encoding 3D output
## Useful stuff
- unity image capture https://docs.unity3d.com/ScriptReference/Camera.Render.html
- recording screenshits https://answers.unity.com/questions/22954/how-to-save-a-picture-take-screenshot-from-a-camer.html