3D Reconstruction in the Wild

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 Intro01:30: What are Duplicate Scene Structures and How to Avoid Them14:30: How Jared used 100 million crowdsourced photos to 3d reconstruct 12,903 landmarks27:10: The benefits of capturing video for 3D reconstruction31:30: The benefits of using a drone to capture stills for 3D reconstruction34:20: Considerations for using installed cameras for 3d reconstruction38:30: How to work with sun issues44:25: Determining how far from the object you should be when capturing images50:35: How to capture objects with reflective surfaces53:40: How work around scene obstructions57:20: What cameras you should useJared Heinly’s Academic Papers and ProjectsPaper: Correcting the Duplicate Scene Structure In Sparse 3D ReconstructionProject: Reconstructing the World in Six DaysVideo: Reconstructing the world in Six DaysFollow Jared Heinly on TwitterFollow Jonathan Stephens on TwitterThis 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: https://www.everypoint.io

There are no comments yet.

Please log in to write the first comment.