search

FangGet / PackNet-SFM-PyTorch

A Pytorch implementation(unofficial) for paper "PackNet-SfM: 3D Packing for Self-Supervised Monocular Depth Estimation"
GNU General Public License v3.0
21 stars 7 forks source link

Reconstruction #8

Open EmreOzkose opened 4 years ago

EmreOzkose commented 4 years ago

Hi, Thank you for code!

I could not see reconstruction code. Would you say&share steps for reconstruction (as we can see in the last part of the video)?

Thanks in advance

FangGet commented 4 years ago

Sorry, as this repo has many differences from origin repo:packnet-sfm(code published), please go to origin repo for more detail.

For a 3D view, you can combine camera intrinsic, color, depth and pose to project pixel on image to world coordinate, it's a simple operation.

EmreOzkose commented 4 years ago

I wrote a basic code to visualize depth map. Implementation may help ros&rviz beginners :) 3D-ros-visualization-of-depth-maps.