In this paper, we propose a new method for interactive motion control with a multi-touch interface. A user of our system can touch and drag character’s body parts to control its motion. The character’s full body motion is driven by our interactive motion control model based on the movement of a few body parts which are directly manipulated by the user via the multi-touch interface. We propose a...

We propose a CNN-based approach for 3D human body pose estimation from single RGB images, that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data. We propose novel CNN supervision techniques, using a regularization structure while training that extends the concept of multi-level skip connections, and leverage first and...

We present a novel approach for 3D human body shape model adaptation to a sequence of multi-view images, given an initial shape model and initial pose sequence. In a first step, the most informative frames are determined by optimization of an objective function that maximizes a shape–texture likelihood function and a pose diversity criterion (i.e. the model surface area that lies close to the o...

For many practical applications, it is sufficient to estimate coarse head to infer gaze direction. Indeed for any application in which the camera is situated unobtrusively in an overhead corner, the only possible inference is coarse pose because of the limitations of the quality and resolution of the incoming data. However, the vast majority of research in head pose estimation deals with tracki...

This paper addresses pixel-level segmentation of a human body from a single image. The problem is formulated as a multi-region segmentation where the human body is constrained to be a collection of geometrically linked regions and the background is split into a small number of distinct zones. We solve this problem in a Bayesian framework for jointly estimating articulated body pose and the pixe...

We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem. Our large and highly varied training dataset allows the classifi...

We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem. Our large and highly varied training dataset allows the classifi...

We propose a generative framework for 3D human pose estimation that is able to operate on both individual point sets and sequential depth data. We formulate human pose estimation as a point set registration problem, where we propose three new approaches to address several major technical challenges in this research. First, we integrate two registration techniques that have a complementary natur...

Capturing visual human-centered information is a fundamental input source for effective and successful human-robot interaction (HRI) in dynamic multi-party social settings. Torso and head pose, as forms of nonverbal communication, support the derivation people’s focus of attention, a key variable in the analysis of human behaviour in HRI paradigms encompassing social aspects. Towards this goal,...

The cognitive advantage of imagined spatial transformations of the human body over that of more unfamiliar objects (e.g., Shepard-Metzler [S-M] cubes) is an issue for validating motor theories of visual perception. In 6 experiments, the authors show that providing S-M cubes with body characteristics (e.g., by adding a head to S-M cubes to evoke a posture) facilitates the mapping of the cognitiv...