Standard video does not capture the 3D aspect of human motion, which is important for comprehension of motion that may be ambiguous. In this paper, we apply augmented reality (AR) techniques to give viewers insight into 3D motion by allowing them to manipulate the viewpoint of a motion sequence of a human actor using a handheld mobile device. The motion sequence is captured using a single RGB-D sensor, which is easier for a general user, but presents the unique challenge of synthesizing novel views using images captured from a single viewpoint. To address this challenge, our proposed system reconstructs a 3D model of the actor, then uses a combination of the actor's pose and viewpoint similarity to find appropriate images to texture it. The system then renders the 3D model on the mobile device using visual SLAM to create a map in order to use it to estimate the mobile device's camera pose relative to the original capturing environment. We call this novel view of a moving human actor a reenactment, and evaluate its usefulness and quality with an experiment and a survey.

Reconstruction of the shape and motion of humans from RGB-D is a challenging problem, receiving much attention in recent years. Recent approaches for full-body reconstruction use a statistic shape model, which is built upon accurate fullbody scans of people in skin-tight clothes, to complete invisible parts due to occlusion. Such a statistic model may still be fit to an RGB-D measurement with loose clothes but cannot describe its deformations, such as clothing wrinkles. Observed surfaces may be reconstructed precisely from actual measurements, while we have no cues for unobserved surfaces. For fullbody reconstruction with loose clothes, we propose to use lower dimensional embeddings of texture and deformation referred to as eigen-texturing and eigen-deformation, to reproduce views of even unobserved surfaces. Provided a full-body reconstruction from a sequence of partial measurements as 3D meshes, the texture and deformation of each triangle are then embedded using eigen-decomposition. Combined with neural-network-based coefficient regression, our method synthesizes the texture and deformation from arbitrary viewpoints. We evaluate our method using simulated data and visually demonstrate how our method works on real data.

When observing a person (an actor) performing or demonstrating some activity for the purpose of learning the action, it is best for the viewers to be present at the same time and place as the actor. Otherwise, a video must be recorded. However, conventional video only provides two-dimensional (2D) motion, which lacks the original third dimension of motion. In the presence of some ambiguity, it may be hard for the viewer to comprehend the action with only two dimensions, making it harder to learn the action. This paper proposes an augmented reality system to reenact such actions at any time the viewer wants, in order to aid comprehension of 3D motion. In the proposed system, a user first captures the actor's motion and appearance, using a single RGB-D camera. Upon a viewer's request, our system displays the motion from an arbitrary viewpoint using a rough 3D model of the subject, made up of cylinders, and selecting the most appropriate textures based on the viewpoint and the subject's pose. We evaluate the usefulness of the system and the quality of the displayed images by user study.

Abstract. We propose ReMagicMirror, a system to help people learn actions (e.g., martial arts, dances). We first capture the motions of a teacher performing the action to learn, using two RGB-D cameras. Next, we fit a parametric human body model to the depth data and texture it using the color data, reconstructing the teacher's motion and appearance. The learner is then shown the ReMagicMirror system, which acts as a mirror. We overlay the teacher's reconstructed body on top of this mirror in an augmented reality fashion. The learner is able to intuitively manipulate the reconstruction's viewpoint by simply rotating her body, allowing for easy comparisons between the learner and the teacher. We perform a user study to evaluate our system's ease of use, effectiveness, quality, and appeal.

No abstract