Jump
Robert Anderson, David Gallup, Jonathan T. Barron et al. · ACM Transactions on Graphics · 2016
We present Jump, a practical system for capturing high resolution, omnidirectional stereo (ODS) video suitable for wide scale consumption in currently available virtual reality (VR) headsets. Our system consists of a video camera built using off-the-shelf components and a fully automatic stitching pipeline capable of capturing video content in the ODS format. We have discovered and analyzed the distortions inherent to ODS when used for VR display as well as those introduced by our capture method and show that they are small enough to make this approach suitable for capturing a wide variety of scenes. Our stitching algorithm produces robust results by reducing the problem to one of pairwise image interpolation followed by compositing. We introduce novel optical flow and compositing methods designed specifically for this task. Our algorithm is temporally coherent and efficient, is currently running at scale on a distributed computing platform, and is capable of processing hours of footage each day.
Cited by 225 works. doi:10.1145/2980179.2980257
Authors
- David Gallup
- Jonathan T. Barron
- Janne Kontkanen
- Noah Snavely
- Carlos Hernández
- Sameer Agarwal
- Steven M. Seitz
References
- Multiple View Geometry in Computer Vision
- An Iterative Image Registration Technique with an Application to Stereo Vision
- Determining optical flow
- Determining Optical Flow
- Light field rendering
- Compositing digital images
- A Database and Evaluation Methodology for Optical Flow
- Compositing digital images
- SIFT Flow: Dense Correspondence across Scenes and Its Applications
- High-quality video view interpolation using a layered representation