In dual-frame video coding, one long-term reference (LTR) and one short-term reference (STR) frames are used for motion estimation and compensation. In previous work, it was shown...
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 extends the so called generalized in-scale coding technique developed in our previous work to a macroblock-based adaptive in-scale motion compensation framework for H...
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
— We present a probabilistic framework for visual correspondence, inertial measurements and Egomotion. First, we describe a simple method based on Gabor filters to produce corre...