We present local and nonlocal algorithms for video denoising based on discrete regularization on graphs. The main difference between video and image denoising is the temporal redu...
This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
The Active Capture demonstration is part of a new computational media production paradigm that transforms media production from a manual mechanical process into an automated compu...
Computer users have tasks they need to perform, and are therefore motivated to overcome poorly designed interfaces. With video games, there is no external motivation for the task ...
We present the 3D Video Recorder, a system capable of recording, processing, and playing three–dimensional video from multiple points of view. We first record 2D video streams f...