3D Reconstruction in the Wild - Computer Vision Decoded Ep. 3

In this episode of Computer Vision Decoded, we sit down with Jared Heinly, Chief Scientist at EveryPoint, to discuss 3D reconstruction in the wild. What does “in the wild” mean? This means 3D reconstructing objects and scenes in non-controlled environments where you may have limitations with lighting, access, reflective surfaces, etc.
00:00 Intro
01:30: What are Duplicate Scene Structures and How to Avoid Them
14:30: How Jared used 100 million crowdsourced photos to 3d reconstruct 12,903 landmarks
27:10: The benefits of capturing video for 3D reconstruction
31:30: The benefits of using a drone to capture stills for 3D reconstruction
34:20: Considerations for using installed cameras for 3d reconstruction
38:30: How to work with sun issues
44:25: Determining how far from the object you should be when capturing images
50:35: How to capture objects with reflective surfaces
53:40: How work around scene obstructions
57:20: What cameras you should use
Jared Heinly’s Academic Papers and Projects
Paper: Correcting the Duplicate Scene Structure In Sparse 3D Reconstruction - www.cs.unc.edu...
Project: Reconstructing the World in Six Days - www.cs.unc.edu...
Video: Reconstructing the world in Six Days: • Reconstructing the Wor...
Follow Jared Heinly on Twitter: / jaredheinly
Follow Jonathan Stephens on Twitter at: / jonstephens85
This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: www.everypoint.io

[@AlejandroFranceschi]

I’m loving all of these videos. These are really important, and you’re so early in this space. This is going to be invaluable training for larger groups of people in the near future.

[@EveryPoint]

Thank you! We often find that he biggest hurdle to 3D reconstruction from imagery is learning how to capture scenes properly.

[@henryreichhold6330]

Great, answers so many questions!

[@diodin8587]

Any good paper for 3d reconstruction from video other than image collections?

[@Mr4DMAGNUM]

Jonathan - sent message on linkedin also as we are connected but i need to talk to you guys and share what we are trying to build.