The function performed by many objects can be expressed in terms of the constraints they impose on the motion of other objects. Cam shafts, worm gears, vises, robot grippers, wrenches and bolt heads are all examples of a class of objects whose shapes are designed to constrain relative motion. In general, objects we consider to be useful are those that support, guide, or constrain the motions of...

Typical tracking algorithms exploit temporal coherence, in the sense of expecting only small object motions. Even without exact knowledge of the scene, additional spatial coherence can be exploited by expecting only a rigid 3d motion. Feature tracking will benefit from knowing about this rigidity of the scene, especially if individual features cannot be tracked by themselves due to occlusions o...

Many compelling applications would become feasible if novice users had the ability to synthesize high quality human motion based only on a simple sketch and a few easily specified constraints. Motion graphs and their variations have proven to be a powerful tool for synthesizing human motion when only a rough sketch is given. Motion graphs are simple to implement, and the synthesis can be fully ...

Motion is an important signal for agents in dynamic environments, but learning to represent motion from unlabeled video is a difficult and underconstrained problem. We propose a model of motion based on elementary group properties of transformations and use it to train a representation of image motion. While most methods of estimating motion are based on pixel-level constraints, we use these gr...

Responsive motion generation of avatars who have physical interactions with their environment is a key issue in VR and video games. We present a performance-driven avatar control interface with physicallybased motion retrieval. When the interaction between the user-controlled avatar and its environment is going to happen, the avatar has to select the motion clip that satisfies both kinematic an...