On-a-slant village was inhabited by the Mandan, a sedentary native north American tribe, up until the late18th century. The on-a-slant "virtual village" has been constructed by the Worldwide Web Instructional Committee at North Dakota State University using archaeological records and other source materials to authenticallyre-create that space with 3D-rendered graphics. The environment now serves as an exploratory, immersive environment for teaching middle-school students about long-ago society. This paper describes the construction of the virtual village and its earth lodges, the software agent avatars who inhabit the space, and the role-playing game the students play in order to learn about the Mandan and their culture. Data collected over three years show that significant learning is accomplished through playing the on-a-slant game.

We build word models for American Sign Language (ASL) that transfer between different signers and different aspects. This is advantageous because one could use large amounts of labelled avatar data in combination with a smaller amount of labelled human data to spot a large number of words in human data. Transfer learning is possible because we represent blocks of video with novel intermediate discriminative features based on splits of the data. By constructing the same splits in avatar and human data and clustering appropriately, our features are both discriminative and semantically similar: across signers similar features imply similar words. We demonstrate transfer learning in two scenarios: from avatar to a frontally viewed human signer and from an avatar to human signer in a 3/4 view.

We capture the shape of moving cloth using a custom set of color markers printed on the surface of the cloth. The output is a sequence of triangle meshes with static connectivity and with detail at the scale of individual markers in both smooth and folded regions. We compute markers' coordinates in space using correspondence across multiple synchronized video cameras. Correspondence is determined from color information in small neighborhoods and refined using a novel strain pruning process. Final correspondence does not require neighborhood information. We use a novel data driven hole-filling technique to fill occluded regions. Our results include several challenging examples: a wrinkled shirt sleeve, a dancing pair of pants, and a rag tossed onto a cup. Finally, we demonstrate that cloth capture is reusable by animating a pair of pants using human motion capture data.

We demonstrate a method for reconstructing the shape of a deformed surface from a single view. After decomposing an image into irradiance and albedo components, we combine normal cues from shading and texture to produce a field of unambiguous normals. Using these normals, we reconstruct the 3D geometry. Our method works in two regimes: either requiring the frontal appearance of the texture or building it automatically from a series of images of the deforming texture. We can recover geometry with errors below four percent of object size on arbitrary textures, and estimate specific geometric parameters using a custom texture even more accurately.