Using reflections to see the world from new points of view | MIT News | Massachusetts Institute of Technology
MIT researchers developed a computer vision technique that uses reflections to turn any object in a scene into a camera, allowing an observer to view the scene from that object’s point of view. The machine-learning method lets the user place a virtual camera anywhere into a scene, enabling one to see around corners or obstructions that would otherwise block the observer’s view.
A new computer vision system turns any shiny object into a camera of sorts, enabling an observer to see around corners or beyond obstructions. Adam Zewe | MIT News Office Publication Date : May 10, 2023 Press Inquiries Press Contact : Abby Abazorius Email: abbya@mit.edu Phone: 617-253-2709 MIT News Office Media Download ↓ Download Image Caption : Researchers from MIT and Rice University have created a computer vision technique that leverages reflections to image the world by using them to turn glossy objects into “cameras,” enabling a user to see the world as if they were looking through the “
Explore this link on the map →saved by
related reading
- NeRF: Neural Radiance Fieldsmatthewtancik.com
- Lights and Shadows – Bartosz Ciechanowskiciechanow.ski
- Removing window reflections in Adobe Camera Raw | Adobe Blogblog.adobe.com
- Neural radiance field - Wikipediaen.wikipedia.org
- Machine Learning for Inverse Graphics – Scene Representation Groupscenerepresentations.org
- A New Trick Lets Artificial Intelligence See in 3D | WIREDwired.com
- 3D Gaussian Splatting for Real-Time Radiance Field Renderingrepo-sam.inria.fr
- Foundations of Computer Visionvisionbook.mit.edu
- Ray Tracing in One Weekendraytracing.github.io
- Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dresearch.nvidia.com
- 1 The Challenge of Vision – Foundations of Computer Visionvisionbook.mit.edu
- Non-line-of-sight imaging using phasor-field virtual wave optics | Naturenature.com