SCA: Symposium on Computer Animation - Posters and Showcases
Permanent URI for this community
Browse
Browsing SCA: Symposium on Computer Animation - Posters and Showcases by Title
Now showing 1 - 20 of 38
Results Per Page
Sort Options
Item Attachment-Based Character Deformation(ACM, 2017) Toothman, Nick; Neff, Michael; Bernhard Thomaszewski and KangKang Yin and Rahul NarainWhile advancements have made it easier to work with digital characters, it remains difficult to author animations that display the free and highly expressive shape change that characterize hand-drawn animation.We present a deformation method that combines skeletal control and free shape change in a single framework, along with an intuitive, sketch-based interface. By finding attachment points between the mesh and skeleton, we enable con gurable skeleton and surface-based deformations, and avoid common skinning artifacts. Use of sketch-based interfaces and graphics hardware make both skeletal and mesh deformation simple to control and fast enough for interactive use.Item Automated Regression Tests for Character Animation Systems(ACM, 2017) Mohr-Daurat, Hubert; Bernhard Thomaszewski and KangKang Yin and Rahul NarainWe present a process to verify code changes in an animation system by using regression tests which guarantee to cover every combination of animation features used in production. For this, we need to identify the untested combinations of animation features, create an immutable set of animation data which is representative of it, and when performing the tests, automatically compare the difference in the generated poses at each revision of the code.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 A Choreographic Authoring System for Character Dance Animation Reflecting a User's Preference(The Eurographics Association, 2016) Kakitsuka, Ryo; Tsukuda, Kosetsu; Fukayama, Satoru; Iwamoto, Naoya; Goto, Masataka; Morishima, Shigeo; Jan BenderWe propose a new system for constructing character dance animation by considering animator's preferences. First, a user of the proposed system assigns a preferred motion, obtained through a searching algorithm, to arbitrary part in the music. Then the proposed system automatically assigns motions to the other remaining parts of the music by using motions in a database. By this system, we can create a new dance performance for character animation considering a user's preference.Item Comparing Traditional Key Frame and Hybrid Animation(ACM, 2017) Ahlström, Eric; Holmqvist, Lucas; Goswami, Prashant; Bernhard Thomaszewski and KangKang Yin and Rahul NarainIn this research the authors explore a hybrid approach which uses the basic concept of key frame animation together with procedural animation to reduce the number of key frames needed for an animation clip. The two approaches are compared by conducting an experiment where the participating subjects were asked to rate them based on their visual appeal.Item Contact and Human Dynamics from Monocular Video(The Eurographics Association, 2020) Rempe, Davis; Guibas, Leonidas J.; Hertzmann, Aaron; Russell, Bryan; Villegas, Ruben; Yang, Jimei; Holden, DanielExisting methods for human motion from video predict 2D and 3D poses that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetrating the ground and bodies leaning at extreme angles. We present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input. We first estimate ground contact timings with a neural network which is trained without hand-labeled data. A physicsbased trajectory optimization then solves for a physically-plausible motion, based on the inputs. We show this process produces motions that are more realistic than those from purely kinematic methods for character animation from dynamic videos. A detailed report that fully describes our method is available at geometry.stanford.edu/projects/human-dynamics-eccv-2020.Item Coordinating Full-Body Interactions with the Environment(ACM, 2017) Juarez-Perez, Alain; Kallmann, Marcelo; Bernhard Thomaszewski and KangKang Yin and Rahul NarainWe present a methodology for synthesizing coordinated full-body motions in order to achieve autonomous virtual characters capable of interacting with the environment while walking. Starting with a parameterized walking controller and a set of mocap examples our method is then able to coordinate upper-body interactions with the walking controller in order to achieve full-body object interactions in generalized situations.Item Creating a Realistic Face Image from a Cartoon Character(The Eurographics Association, 2016) Nakamura, Masanori; Yamaguchi, Shugo; Fukusato, Tsukasa; Morishima, Shigeo; Jan BenderWe propose a method of creating a realistic face image from a 2D non-realistic character such as a cartoon. Our system allows us to create a high quality face image that is applicable for some application such as 3D character animation. Our system uses two key algorithms; one is an algorithm for synthesizing a novel face image without the warping process, and the other is a searching algorithm, which search each optimal patch from the database based on gradient distribution.Item Cubification and Animation of Artistic Shapes(ACM, 2017) Corker-Marin, Quentin; Adzhiev, Valery; Pasko, Alexander; Bernhard Thomaszewski and KangKang Yin and Rahul NarainThis poster describes an original approach to creating static and dynamic sculptures in a cubist style.We propose a novel method for faceting and local distortion thus adding cubist features and generating time-variant sculptural shapes. We introduce the concept of a 4D cubist camera for blending multiple projections from 4D spacetime to 3D space.We describe a practical pipeline embracing all the main phases of production of static and dynamic cubist shapes. The proposed techniques are implemented and experimental results are presented.Item Data-driven Finger Motion Synthesis with Interactions(The Eurographics Association, 2016) Bitan, Moshe; Jörg, Sophie; Kraus, Sarit; Jan BenderThe film and video-game industries' rapidly increasing demand for realistic virtual characters is pushing for the development of fast and efficient character animation techniques. The use of motion capture has become an industry standard. While motion capture systems allow the production of high fidelity full-body motions, in most cases, the complex finger movements are later animated manually. Several methods have been suggested to automatically synthesize finger motions.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 Efficient Storyboarding in 3D Game Engines(The Eurographics Association, 2016) Gouvatsos, Alexandros; Xiao, Zhidong; Pang, Keith; Marsden, Neil; Ark, Danny Van der; Hibbert, Jerry; Zhang, Jian J.; Jan BenderGetting an accurate match between initial storyboards and the 3D layout is difficult, given today's reality of multi-site productions. While big studios have the luxury of re-iterating over the 3D layout of a shot, smaller studios with smaller budgets have limited attempts to get it right. Going back to make corrections is the difference between delivering on time or going over budget. Studios can avoid mistakes and deliver on time by storyboarding directly in 3D, with the help of game engines. Thousands of minutes of animation have been created in this way, for productions such as "Bob the Builder" and "Tree Fu Tom".Item Efficient Unified Stokes using a Polynomial Reduced Fluid Model(The Eurographics Association, 2020) Panuelos, Jonathan; Goldade, Ryan; Batty, Christopher; Michels, Dominik L.Unsteady Stokes solvers, coupling stress and pressure forces, are a key component of accurate free surface simulators for highly viscous fluids. Because of the simultaneous application of stress and pressure terms, this creates a much larger system than the standard decoupled approach. We propose a reduced fluid model wherein interior regions are represented with incompressible polynomial vector fields. Sets of standard grid cells are consolidated into super-cells, each of which are modelled using only 26 degrees of freedom. This reduced model retains desirable behaviour of the full Stokes system with smaller computational cost.Item Fast Eulerian Fluid Simulation In Games Using Poisson Filters(The Eurographics Association, 2020) Rabbani, Amir H.; Khiat, Soufiane; Holden, DanielWe present separable Poisson filters to accelerate the projection step in Eulerian fluid simulation. These filters are analytically computed offline and are easy to integrate into any fluid algorithm with a Poisson pressure computation step. We take advantage of the recursive structure of the Jacobi method to construct and then reduce a kernel that is used to solve the Poisson pressure entirely on GPU. Our method demonstrates promising speedups that scale well with both the grid resolution and the target Jacobi iteration.Item Friction Sound Synthesis of Deformable Objects based on Adhesion Theory(The Eurographics Association, 2016) Nakatsuka, Takayuki; Morishima, Shigeo; Jan BenderFriction sound is one of the closest sounds for us in any situations. Most of those sounds are created by Foley artists in computer animations. However, synthesizing sounds in all scenes need technical skills and take high costs. In this research, we propose a novel physically-based approach to synthesize various kinds of friction sounds based on dynamics simulation.Item Frontmatter: ACM SIGGRAPH / Eurographics Symposium of Computer Animation 2018 - Posters(The Eurographics Association, 2018) ; Skouras, MelinaItem Human Grasping Interaction Capture and Analysis(ACM, 2017) Verider, Benjamin; Andrews, Sheldon; Kry, Paul G.; Bernhard Thomaszewski and KangKang Yin and Rahul NarainWe design a system to capture, clean, and segment a high quality database of hand based grasping and manipulation. We capture interactions with a large collection of everyday objects. Optical marker-based motion capture and glove data are combined in a physics-based filter to improve the quality of thumb motion. Sensors stitched into our glove provide recordings of the pressure image across the fingers and the palm. We evaluate di erent segmentation techniques for processing motion and pressure data. Finally, we describe examples that explain how the data will be useful in applications such as virtual reality and the design of physics-based control of virtual and robotic hands.Item Interactive Wood Fracture(The Eurographics Association, 2020) Hädrich, Torsten; Scheffczyk, Jan; Palubicki, Wojciech; Pirk, Sören; Michels, Dominik L.; Michels, Dominik L.Abstract We propose a new approach for the simulation of wood as anisotropic material that takes its inherent fiber structure into account. Our approach is based on the Position-based Dynamics framework. We use the Shape Matching approach as the basis for modeling the isotropic attribute of wood. For simulating anisotropic behavior we employ a fiber model based on the Cosserat rod theory. Our approach supports dynamic fracturing and captures typical breaking patterns of wood.Item 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.