SCA 18: Posters
Permanent URI for this collection
Browse
Browsing SCA 18: Posters by Title
Now showing 1 - 8 of 8
Results Per Page
Sort Options
Item Capturing Floor Exercise from Multiple Panning-Zooming Cameras(The Eurographics Association, 2018) Kobayashi, D.; Yamamoto, Masanobu; Skouras, MelinaBy panning and zooming camera, a system of the multiple cameras can obtain wider range of common field of views. It means that an image based motion capture system can measure bodies in motion of wider range. To do so, a key idea is a camera calibration by matching the panned and zoomed image with a panoramic image of the background. We show an experiment of motion capture of a gymnastic athlete in floor exercise by the calibrated cameras.Item Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data(The Eurographics Association, 2018) Noshaba, Cheema; Hosseini, Somayeh; Sprenger, Janis; Herrmann, Erik; Du, Han; Fischer, Klaus; Slusallek, Philipp; Skouras, MelinaSemantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments. Afterwards, additional methods like statistical modeling can be applied to each group of structurally-similar segments to learn an abstract motion manifold. The segmentation task however often remains a manual task, which increases the effort and cost of generating large-scale motion databases. We therefore propose an automatic framework for semantic segmentation of motion capture data using a dilated temporal fully-convolutional network. Our model outperforms a state-of-the-art model in action segmentation, as well as three networks for sequence modeling. We further show our model is robust against high noisy training labels.Item Frontmatter: ACM SIGGRAPH / Eurographics Symposium of Computer Animation 2018 - Posters(The Eurographics Association, 2018) ; Skouras, MelinaItem Latent Motion Manifold with Sequential Auto-Encoders(The Eurographics Association, 2018) Jang, Deok-Kyeong; Lee, Sung-Hee; Skouras, MelinaWe propose the sequential autoencoders for constructing latent motion manifold. Sequential autoencoders minimize the difference between the ground truth motion space distribution and reconstructed motion space distribution sampled from the latent motion manifold. Our method is based on sequence-to-sequence model for encoding the temporal information of human motion. We also adopt Wasserstein regularizer for matching encoded training distribution to the prior distribution of motion manifold. Our experiments show that randomly sampled points from trained motion manifold distribution become natural and valid motions.Item Local Models for Data Driven Inverse Kinematics of Soft Robots(The Eurographics Association, 2018) Holsten, Fredrik; Darkner, Sune; Engell-Nørregård, Morten P.; Erleben, Kenny; Skouras, MelinaSoft robots are attractive because they have the potential of being safer, faster and cheaper than traditional rigid robots. If we can predict the shape of a soft robot for a given set of control parameters, then we can solve the inverse problem: to find an optimal set of control parameters for a given shape. This work takes a data-driven approach to create multiple local inverse models. This has two benefits: (1) We overcome the reality gap and (2) we gain performance and naive parallelism from using local models. Furthermore, we empirically prove that our approach outperforms a higher order global model.Item Untangling Layered Garments: An Implicit Approach(The Eurographics Association, 2018) Buffet, Thomas; Rohmer, Damien; Cani, Marie-Paule; Skouras, MelinaThe efficient animation of layers of garments is a challenging task, as it requires handling collisions and contacts between multiple thin surfaces, which may be difficult to untangle once inter-penetrations have occurred. We propose a novel geometric approach, based on implicit surfaces, to robustly handle such situations. At each animation step, our method converts the possibly intersecting garment surfaces to an implicit representation. They are then combined using a new binary operator that guarantees, as output, collision free states of the surfaces. In addition to a precise modeling of contact situations, our method enables to model the relative influence of each cloth layer, based on their relative stiffnesses and thicknesses.Item Viewpoint Selection for Liquid Animations(The Eurographics Association, 2018) Suzuki, Chihiro; Kanai, Takashi; Skouras, MelinaWe propose a viewpoint selection method for time-varying liquid shapes in order to select the best viewpoint for liquid animations. First, viewpoint evaluation is performed by a combination of three evaluation terms; occlusion term, spatial feature term, and temporal feature term, and the viewpoint having the maximum evaluation value is selected as the “best viewpoint”. Through various experiments, it was confirmed that the results of this method is consistent with human intuition and that it can select viewpoints independent of the resolution of liquid meshes.Item VR Kino+Theatre: From the Ancient Greeks Into the Future of Media(The Eurographics Association, 2018) Velho, Luiz; Carvalho, Leonardo; Lucio, Djalma; Skouras, MelinaVR Kino+Theatre is a media platform that combines theatrical performance with live cinema using virtual reality technology.