4 papers
The Cone of Silence: Speech Separation by Localization
Teerapat Jenrungrot, Vivek Jayaram, Steve Seitz +1
Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers. At the core o…
Background Matting: The World is Your Green Screen
Soumyadip Sengupta, Vivek Jayaram, Brian Curless +2
We propose a method for creating a matte -- the per-pixel foreground color and alpha -- of a person by taking photos or videos in an everyday setting with a handheld camera. Most e…
Real-Time Camera Pose Estimation for Sports Fields
Leonardo Citraro, Pablo Márquez-Neila, Stefano Savarè +6
Given an image sequence featuring a portion of a sports field filmed by a moving and uncalibrated camera, such as the one of the smartphones, our goal is to compute automatically i…
Source Separation with Deep Generative Priors
Vivek Jayaram, John Thickstun
Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models c…