Real-time 3D Reconstruction at Scale using Voxel Hashing
HTML-код
- Опубликовано: 4 ноя 2024
- Project webpage: research.micros...
Online 3D reconstruction is gaining newfound interest due to the availability of real-time consumer depth cameras. The basic problem takes live overlapping depth maps as input and incrementally fuses these into a single 3D model. This is challenging particularly when real-time performance is desired without trading quality or scale. We contribute an online system for large and fine scale volumetric reconstruction based on a memory and speed efficient data structure.
really awesome work!
*OFF ITS FUCKING HEAD!*
Fresh off the Doc, this is some back to the future shit!
this is really wonderful!
Is there a way to use this for mac computers as well, in opengl format? Though I know it is a microsoft technology.
What type of depth sensing technology is being used?
+Erran G most likely two different camera lenses and binocular vision, like how the kinect or our eyes work. Either that, or lasers. But I doubt lasers for a camera like this.
+Bungis Albondigas kinect doesnt work as our eyes, i.e. it doesn use stereo vision.
By using the IR laser as an augmented camera (knowing the point array from the IR laser POV), kinect uses a stereo matching algorithm to match this to the image from the IR camera to work as our eyes,
i.e it uses stereo vision by way of one real camera and one simulated camera.
could I use this in something like unreal engine to speed up location and device modeling?
someone beat me to my comment. i am worried.
You notice this was 2014, it's sad we haven't seen this used more.
it is used Check out Google & Lenovo Latest Project Pro Phab 2 and be amazed at utilizing this tech in Augmented reality applications