madhawav

This can detect rooms as polygons, doors/windows as line segments and bounding boxes around objects (e.g. cabinets, sinks etc. indicated on floorplans).

Comment · 5 years ago

For instance, look at this sample 3d scanned house: https://matterport.com/en-gb/media/2486. Make sure to switch to the doll-house view from the toolbar. There are many holes in the scan.

Comment · 5 years ago

Thank you.

Comment · 5 years ago

This is definitely a thought I have considered. It could potentially ease lot of hassle related to 3D scanning of houses by real-estate companies. Very often, those scans require expensive equipment, professional expertise to use those equipment and considerable time and effort to capture the entire residence. Even then,you will find many holes in those scans and floating debris. With our work, one only needs a sketch of the floorplan and photos taken from that house. Plan2Scene will use data to infer appearance of unseen surfaces.

Comment · 5 years ago

Thank you!

Comment · 5 years ago

Estimating the global camera pose using non-overlapping photos is a challenging problem. This is doable if the photos densely cover the house (e.g. video frames).

However, if the global camera poses are available, we can detect surfaces in photos and project them reasonably well into 3D. In the past, I have used this work to achieve something similar: https://github.com/NVlabs/planercnn

Comment · 5 years ago

Hi, This is because the Rent3D dataset we extend has a "non-commercial use only" term.

Comment · 5 years ago

I'm the first author of this, happy to answer any questions. It's great to see this on HN.

PS. I'll be graduating this July with my masters.