Multiview video in “texture-plus-depth” format enables decoder to synthesize freely chosen intermediate views for enhanced visual experience. Nevertheless, transmission of multiple texture and depth maps over bandwidthconstrained and loss-prone networks is challenging, especially for conferencing applications with stringent deadlines. In this paper, we examine the problem of loss-resilient codi...

Following another person's gaze in order to achieve joint attention is an important skill in human social interactions. This work analyzes geometric aspects of the gaze following problem and proposes a learning-based computational model for the emergence of gaze following skills in infants. The model acquires advanced gaze following skills by learning associations between caregiver head poses a...

Depth-image-based rendering (DIBR) is a method to represent a stereoscopic content. The DIBR consists of a monoscopic center view and an associated per-pixel depth map. Using these two components and given depth condition from a user, the DIBR renders left and right views. The advantages of DIBR are numerous. The user can choose not only the monoscopic or stereoscopic view selectively, but also...

Addition of anionic polyacrylamide (PAM) to agricultural irrigation water can dramatically reduce erosion of soils. However, the toxicity of PAM to aquatic life, while often claimed to be low, has not been thoroughly evaluated. Five PAM formulations, including two oil-based products, one water-based product, one granular product and one tablet product, were evaluated for acute and/or chronic to...

Most P losses from surface-irrigated fields occur via runoff, are associated with eroded sediment, and can be minimized by eliminating irrigation-induced erosion. A convenient new practice that eliminates furrow irrigation-induced soil losses uses a high molecular weight, anionic polyacrylamide (PAM) applied to initial irrigation inflows. We hypothesized that, compared to control furrows, PAM t...

In this paper, we propose a method to extract depth from motion, texture and intensity. We first analyze the depth map to extract a set of depth cues. Then, based on these depth cues, we process the colored reference video, using texture, motion, luminance and chrominance content, to extract the depth map. The processing of each channel in the Y CRCB−color space is conducted separately. We test...