Search for: All records

In this paper we present AffordIt!, a tool for adding affordances to the component parts of a virtual object. Following 3D scene reconstruction and segmentation procedures, users find themselves with complete virtual objects, but no intrinsic behaviors have been assigned, forcing them to use unfamiliar Desktop-based 3D editing tools. AffordIt! offers an intuitive solution that allows a user to select a region of interest for the mesh cutter tool, assign an intrinsic behavior and view an animation preview of their work. To evaluate the usability and workload of AffordIt! we ran an exploratory study to gather feedback. In the study we utilize two mesh cutter shapes that select a region of interest and two movement behaviors that a user then assigns to a common household object. The results show high usability with low workload ratings, demonstrating the feasibility of AffordIt! as a valuable 3D authoring tool. Based on these initial results we also present a road-map of future work that will improve the tool in future iterations. 

We introduce an interactive system for extracting the geometries of generalized cylinders and cuboids from singleor multiple-view point clouds. Our proposed method is intuitive and only requires the object’s silhouettes to be traced by the user. Leveraging the user’s perceptual understanding of what an object looks like, our proposed method is capable of extracting accurate models, even in the presence of occlusion, clutter or incomplete point cloud data, while preserving the original object’s details and scale. We demonstrate the merits of our proposed method through a set of experiments on a public RGBD dataset. We extracted 16 objects from the dataset using at most two views of each object. Our extracted models represent a high degree of visual similarity to the original objects. Further, we achieved a mean normalized Hausdorff distance of 5.66% when comparing our extracted models with the dataset’s ground truths.