Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning. Since real-world data is notoriously costly to collect, many recent state-of-the-art disentanglement models have heavily relied on synthetic toy data-sets. In this paper, we propose a novel data-set which consists of over 1 million images of physical 3D objects with seven factors of variation, such as object color, shape, size and position. In order to be able to control all the factors of variation precisely, we built an experimental platform where the objects are being moved by a robotic arm. In addition, we provide two more datasets which consist of simulations of the experimental setup. These datasets provide for the first time the possibility to systematically investigate how well different disentanglement methods perform on real data in comparison to simulation, and how simulated data can be leveraged to build better representations of the real world. We provide a first experimental study of these questions and our results indicate that learned models transfer poorly, but that model and hyperparameter selection is an effective means of transferring information to the real world.

We investigated the influence of body shape and pose on the perception of physical strength and social power for male virtual characters. In the first experiment, participants judged the physical strength of varying body shapes, derived from a statistical 3D body model. Based on these ratings, we determined three body shapes (weak, average, and strong) and animated them with a set of power poses for the second experiment. Participants rated how strong or powerful they perceived virtual characters of varying body shapes that were displayed in different poses. Our results show that perception of physical strength was mainly driven by the shape of the body. However, the social attribute of power was influenced by an interaction between pose and shape. Specifically, the effect of pose on power ratings was greater for weak body shapes. These results demonstrate that a character with a weak shape can be perceived as more powerful when in a high-power pose.

The realistic depiction of lifelike virtual humans has been the goal of many movie makers in the last decade. Recently, films such as Tron: Legacy and The Curious Case of Benjamin Button have produced highly realistic characters. In the real-time domain, there is also a need to deliver realistic virtual characters, with the increase in popularity of interactive drama video games (such as L.A. Noire™ or Heavy Rain™ ). There have been mixed reactions from audiences to lifelike characters used in movies and games, with some saying that the increased realism highlights subtle imperfections, which can be disturbing. Some developers opt for a stylized rendering (such as cartoon-shading) to avoid a negative reaction [Thompson 2004]. In this paper, we investigate some of the consequences of choosing realistic or stylized rendering in order to provide guidelines for developers for creating appealing virtual characters. We conducted a series of psychophysical experiments to determine whether render style affects how virtual humans are perceived. Motion capture with synchronized eye-tracked data was used throughout to animate custom-made virtual model replicas of the captured actors.

Rich face models already have a large impact on the fields of computer vision, perception research, as well as computer graphics and animation. Attributes such as descriptiveness, semantics, and intuitive control are desirable properties but hard to achieve. Towards the goal of building such high-quality face models, we present a 3D model-based analysis-by-synthesis approach that is able to parameterize 3D facial surfaces, and that can estimate the state of semantically meaningful components, even from noisy depth data such as that produced by Time-of-Flight (ToF) cameras or devices such as Microsoft Kinect. At the core, we present a specialized 3D morphable model (3DMM) for facial expression analysis and synthesis. In contrast to many other models, our model is derived from a large corpus of localized facial deformations that were recorded as 3D scans from multiple identities. This allows us to analyze unstructured dynamic 3D scan data using a modified Iterative Closest Point model fitting process, followed by a constrained Action Unit model regression, resulting in semantically meaningful facial deformation time courses. We demonstrate the generative capabilities of our 3DMMs for facial surface reconstruction on high and low quality surface data from a ToF camera. The analysis of simultaneous recordings of facial motion using passive stereo and noisy Time-of-Flight camera shows good agreement of the recovered facial semantics.

This paper considers the problem of realizing a 6-DOF closed-loop motion simulator by exploiting an anthropomorphic serial manipulator as motion platform. Contrary to standard Stewart platforms, an industrial anthropomorphic manipulator offers a considerably larger motion envelope and higher dexterity that let envisage it as a viable and superior alternative. Our work is divided in two papers. In this Part I, we discuss the main challenges in adopting a serial manipulator as motion platform, and thoroughly analyze one key issue: the design of a suitable inverse kinematics scheme for online motion reproduction. Experimental results are proposed to analyze the effectiveness of our approach. Part II [1] will address the design of a motion cueing algorithm tailored to the robot kinematics, and will provide an experimental evaluation on the chosen scenario: closed-loop simulation of a Formula 1 racing car.

This paper, divided in two Parts, considers the problem of realizing a 6-DOF closed-loop motion simulator by exploiting an anthropomorphic serial manipulator as motion platform. After having proposed a suitable inverse kinematics scheme in Part I [1], we address here the other key issue, i.e., devising a motion cueing algorithm tailored to the specific robot motion envelope. An extension of the well-known classical washout filter designed in cylindrical coordinates will provide an effective solution to this problem. The paper will then present a thorough experimental evaluation of the overall architecture (inverse kinematics + motion cueing) on the chosen scenario: closed-loop simulation of a Formula 1 racing car. This will prove the feasibility of our approach in fully exploiting the robot motion capabilities as a motion simulator.

Affordable 3D vision is just about to enter the mass market for consumer products such as video game consoles or TV sets. Having depth information in this context is beneficial for segmentation as well as gaining robustness against illumination effects, both of which are hard problems when dealing with color camera data in typical living room situations. Several techniques compute 3D (or rather 2.5D) depth information from camera data such as realtime stereo, time-of-flight (TOF), or real-time structured light, but all produce noisy depth data at fairly low resolutions. Not surprisingly, most applications are currently limited to basic gesture recognition using the full body. In particular, TOF cameras are a relatively new and promising technology for compact, simple and fast 2.5D depth measurements. Due to the measurement principle of measuring the flight time of infrared light as it bounces off the subject, these devices have comparatively low image resolution (176 x 144 ... 320 x 240 pixels) with a high level of noise present in the raw data.

The Uncanny Valley (UV) has become a standard term for the theory that near-photorealistic virtual humans often appear unintentionally erie or creepy. This UV theory was first hypothesized by robotics professor Masahiro Mori in the 1970's [Mori 1970] but is still taken seriously today by movie and game developers as it can stop audiences feeling emotionally engaged in their stories or games. It has been speculated that this is due to audiences feeling a lack of empathy towards the characters. With the increase in popularity of interactive drama video games (such as L.A. Noire or Heavy Rain), delivering realistic conversing virtual characters has now become very important in the real-time domain. Video game rendering techniques have advanced to a very high quality; however, most games still use linear blend skinning due to the speed of computation. This causes a mismatch between the realism of the appearance and animation, which can result in an uncanny character. Many game developers opt for a stylised rendering (such as cel-shading) to avoid the uncanny effect [Thompson 2004]. In this preliminary work, we begin to study the complex interaction between rendering style and perceived trust, in order to provide guidelines for developers for creating plausible virtual characters.

The human face is capable of producing an astonishing variety of expressions—expressions for which sometimes the smallest difference changes the perceived meaning considerably. Producing realistic-looking facial animations that are able to transmit this degree of complexity continues to be a challenging research topic in computer graphics. One important question that remains to be answered is: When are facial animations good enough? Here we present an integrated framework in which psychophysical experiments are used in a first step to systematically evaluate theperceptualquality of several different computer-generated animations with respect to real-world video sequences. The first experiment provides an evaluation of several animation techniques, exposing specific animation parameters that are important to achieve perceptual fidelity. In a second experiment, we then use these benchmarked animation techniques in the context of perceptual research in order to systematically investigate the spatiotemporal characteristics of expressions. A third and final experiment uses the quality measures that were developed in the first two experiments to examine the perceptual impact of changing facial features to improve the animation techniques. Using such an integrated approach, we are able to provide important insights into facial expressions for both the perceptual and computer graphics community.

Regardless of whether the humans involved are virtual or real, well-developed conversational skills are a necessity. The synthesis of interface agents that are not only understandable but also believable can be greatly aided by knowledge of which facial motions are perceptually necessary and sufficient for clear and believable conversational facial expressions. Here, we recorded several core conversational expressions (agreement, disagreement, happiness, sadness, thinking, and confusion) from several individuals, and then psychophysically determined the perceptual ambiguity and believability of the expressions. The results show that people can identify these expressions quite well, although there are some systematic patterns of confusion. People were also very confident of their identifications and found the expressions to be rather believable. The specific pattern of confusions and confidence ratings have strong implications for conversational animation. Finally, the present results provide the information necessary to begin a more fine-grained analysis of the core components of these expressions.