Twitter | Pretraživanje | |
Jonathan Fly 👾
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: pdf: code/weights:
Reply Retweet Označi sa "sviđa mi se" More
Jonathan Fly 👾 1. velj
Odgovor korisniku/ci @jonathanfly
I'd love to see what this does with non-furniture images. Their doesn't output 3D but '' 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.
Reply Retweet Označi sa "sviđa mi se"
jack Lord oatkon 1. velj
Odgovor korisniku/ci @jonathanfly
It reminds me of Sketchup.
Reply Retweet Označi sa "sviđa mi se"
jack Lord oatkon 1. velj
Odgovor korisniku/ci @jonathanfly
Reply Retweet Označi sa "sviđa mi se"