Abstract

Understanding the control forces that drive humans and animals is fundamental to describing their movement. Although physics-based methods hold promise for creating animation, they have long been considered too difficult to design and control. Likewise, recent results in computer vision suggest how physical models, if developed, could be important to human pose tracking.

I will describe the main problems of human motion modeling. I will then present a new approach to control of physics-based characters based on high-level features of human movement. These controllers provide unprecedented flexibility and generality in real-time character control: they are capture many natural properties of human movement; they can be easily modified and applied to new characters; and they can handle a variety of different terrains and tasks, all within a single control strategy.

Until very recently, even making a controller walk without falling down was extraordinarily difficult. This is no longer the case. Our work, together with other recent results in this area, suggests that we are now ready to make great strides in locomotion.

About the speaker

Abstract

The triangle (and the quad) have been the ubiquitous rendering primitives leading to astonishing impact in performance when it comes to rendering. Indeed specialized hardware commodities such as the Graphics Processing Unit (GPU) have survived and performed handsomely.

Recently, however, new forms of input data are also becoming available - three dimensional points, and rich, high resolution digital photographs.  In this talk I will show examples of rendering directly from these heterogeneous data types instead of working in the polygonal domain.

About the speaker

Abstract

Electron microscopes (EM) can now provide the nanometer resolution that is needed to image synapses, and therefore connections, while Light Microscopes (LM) see at the micrometer resolution required to model the 3D structure of the dendritic network. Since both the arborescence and the connections are integral parts of the brain's wiring diagram, combining these two modalities is critically important.

In this talk, I will therefore present our approach to building the dendritic arborescence and to tracking migrating neurons from LM images, as well as to segmenting intra-neuronal structures from EM images.

About the speaker

Abstract

Reasoning about a scene from a photograph is an inherently ambiguous task. This is because a single image in itself does not carry enough information to disambiguate the world that it is depicting. Of course humans have no problems understanding photographs because of all the prior visual experience they can bring to bear on the task. But if our goal is to create computer programs that can do the same, we must first answer a fundamental question: what does it mean to "understand" an image? Is it simply naming the depicted objects? Or is there a need for some deeper understanding of the properties of these objects and the underlying 3D scene? How would we even know if the goal of image understating has been achieved? While at present we don't have good answers to these important questions, in this talk I will present some results suggesting that it might be beneficial to look at image understanding beyond mere object naming.

About the speaker