Animals are an important resource for our society, but unfortunately they are often threatened and over exploited by humans. Computer vision can greatly contribute to animal conservation and wellbeing by providing non-invasive tools for capturing animal behaviour. Animals communicate mostly with body posture and sound, their health conditions are often related to shape changes. In this talk I will present my work on taking a 3D perspective when looking at animals, specifically through generative models of animal shape for 3D pose and shape reconstruction from monocular data.
Dr. Silvia Zuffi is currently a research scientist at IMATI-CNR. She graduated in Electronic Engineering at the University of Bologna in 1995. After graduation, she worked for some time in the industry, where she contributed to realize a system for the forecast of the tide in Venice. Before starting her PhD in 2009, she worked as research scientist at ITC-CNR (Milan, Italy), where she worked on color imaging, specifically multispectral imaging and reproduction, and readability of colored text on Web pages. In 2015, she received her PhD in Computer Science at Brown University, under the supervision of Prof. Michael J. Black. Her research interest is animal and human pose estimation from images and videos, and her main contribution to the field is the exploration of realistic 2D and 3D models of human body shape and 3D models of animals for estimating pose and articulated motion in unconstrained images, videos, and from 3D data.