|
@jonathanfly | |||||
|
Semantic Scene Completion is inferring labels (what something is) and 3D geometry at the same time.
PALnet: Depth Based Semantic Scene Completion with Position Importance Aware Loss
abs: arxiv.org/abs/2001.10709
pdf: arxiv.org/pdf/2001.10709…
code/weights: github.com/UniLauX/PALNet pic.twitter.com/kMFNYA3rP1
|
||||||
|
||||||
|
Jonathan Fly 👾
@jonathanfly
|
1. velj |
|
I'd love to see what this does with non-furniture images. Their test.py doesn't output 3D but 'SscDataLoader.py' has various voxel-related conversions (npz, ply, rle) none of which I know a thing about. May be an easy tweak for anyone who works with voxels.
|
||
|
|
||
|
jack Lord oatkon
@Bookhimdannom1
|
1. velj |
|
It reminds me of Sketchup.
|
||
|
|
||
|
jack Lord oatkon
@Bookhimdannom1
|
1. velj |
|
|
||