SCA: Symposium on Computer Animation - Posters and Showcases

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2630804

Browse

Now showing 1 - 20 of 51

Adaptive Sampling for Simulating Granular Materials
(The Eurographics Association, 2024) Gupta, Samraat; Keyser, John; Zordan, Victor
We present a method for generating simulations of granular materials more quickly within a position based dynamics framework. We do this by combining an adaptive particle sampling scheme with an upsampling approach. This allows for faster simulations in interactive applications, while maintaining visual resolution. Particles are merged or split based on their distance from the boundary, allowing for high details in areas of importance such as the surface and edges. Merging particles into a single particle reduces the number of particles for which collisions have to be simulated, thus reducing the overall simulation time. The adaptive sampling technique is then combined with an upsampling scheme that gives the coarser particle simulation the appearance of much finer resolution.
Art-directable Expressive Oscillation Behavior for Rigged Characters
(The Eurographics Association, 2024) Salem, Karim; Rohmer, Damien; Kalyanasundaram, Niranjan; Zordan, Victor; Zordan, Victor
We propose a method to enrich the animation of rigged characters with exaggerated oscillation behavior triggered by a sudden velocity change. Our approach is based on the extension of Velocity Skinning to space-time deformation, where the deformation is computed from a time-filtered version of the angular velocity of the skeleton. The time-filter is easy to parameterize by artists with respect to frequency, magnitude and attenuation while remaining fully compatible with standard rigged character.
Attachment-Based Character Deformation
(ACM, 2017) Toothman, Nick; Neff, Michael; Bernhard Thomaszewski and KangKang Yin and Rahul Narain
While 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.
Automated Regression Tests for Character Animation Systems
(ACM, 2017) Mohr-Daurat, Hubert; Bernhard Thomaszewski and KangKang Yin and Rahul Narain
We 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.
Brittle Fracture Animation with VQ-VAE-Based Generative Method
(The Eurographics Association, 2024) Huang, Yuhang; Kanai, Takashi; Zordan, Victor
We propose a novel learning-based approach for predicting fractured shapes based on collision dynamics at run-time and seamlessly integrating realistic brittle fracture animations with rigid-body simulations. Our method utilizes BEM brittle fracture simulations to create training data. We introduce generative geometric segmentation, distinct from instance and semantic segmentation, to represent 3D fracture shapes. We adopt the concept of a neural discrete representation learning framework to optimize multiple discrete fractured patterns with a continuous latent code. Additionally, we propose a novel SDF-based cagecutting method to create fragments by cutting the original shape with the predicted fracture pattern. Our experimental results demonstrate that our approach can generate significantly more detailed brittle fractures compared to existing techniques, while reducing computational time typically when compared to traditional simulation methods at comparable resolutions.
Capturing Floor Exercise from Multiple Panning-Zooming Cameras
(The Eurographics Association, 2018) Kobayashi, D.; Yamamoto, Masanobu; Skouras, Melina
By 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.
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 Bender
We 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.
Comparing Traditional Key Frame and Hybrid Animation
(ACM, 2017) Ahlström, Eric; Holmqvist, Lucas; Goswami, Prashant; Bernhard Thomaszewski and KangKang Yin and Rahul Narain
In 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.
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, Daniel
Existing 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.
Coordinating Full-Body Interactions with the Environment
(ACM, 2017) Juarez-Perez, Alain; Kallmann, Marcelo; Bernhard Thomaszewski and KangKang Yin and Rahul Narain
We 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.
Creating a Realistic Face Image from a Cartoon Character
(The Eurographics Association, 2016) Nakamura, Masanori; Yamaguchi, Shugo; Fukusato, Tsukasa; Morishima, Shigeo; Jan Bender
We 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.
Cubification and Animation of Artistic Shapes
(ACM, 2017) Corker-Marin, Quentin; Adzhiev, Valery; Pasko, Alexander; Bernhard Thomaszewski and KangKang Yin and Rahul Narain
This 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.
Data-driven Finger Motion Synthesis with Interactions
(The Eurographics Association, 2016) Bitan, Moshe; Jörg, Sophie; Kraus, Sarit; Jan Bender
The 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.
Data-driven Friction for Real-time Applications
(The Eurographics Association, 2024) Nassif, Loïc; Zoubir, O.; Andrews, Sheldon; Kry, Paul G.; Zordan, Victor
We present a novel data-driven approach for simulating friction between rigid bodies that captures the rich diversity of frictional behaviors that arises due to the complex interactions of micro-asperities of different surfaces. Rather than performing detailed simulations with expensive collision detection, we parameterize our friction model based on aggregate features of pairs of surfaces, such as the distribution of normals from each surfaces, which may be easily computed from a texture-based embedding. Our data-driven model is constructed by conducting real-world planar pushing experiments that capture the friction behavior of many different material pairs, and we then fit this data using a Gaussian process (GP). The trained GP model is then evaluated in a real-time simulation and used to update the limit surface used by the contact solver.
A Differentiable Material Point Method Framework for Shape Morphing
(The Eurographics Association, 2024) Xu, Michael; Song, Chang Yong; Levin, David; Hyde, David; Zordan, Victor
We present a novel, physically-based morphing technique for elastic shapes, leveraging the differentiable material point method (MPM) with space-time control through per-particle deformation gradients to accommodate complex topology changes. This approach, grounded in MPM's natural handling of dynamic topologies, is enhanced by a chained iterative optimization technique, allowing for the creation of both succinct and extended morphing sequences that maintain coherence over time. Demonstrated across various challenging scenarios, our method is able to produce detailed elastic deformation and topology transitions, all grounded within our physics-based simulation framework.
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, Melina
Semantic 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.
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 Bender
Getting 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".
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.
Eurographics/ ACM SIGGRAPH Symposium on Computer Animation - Posters: Frontmatter
(The Eurographics Association, 2024) Zordan, Victor; Zordan, Victor
Fast Eulerian Fluid Simulation In Games Using Poisson Filters
(The Eurographics Association, 2020) Rabbani, Amir H.; Khiat, Soufiane; Holden, Daniel
We 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.

Browse

Browsing SCA: Symposium on Computer Animation - Posters and Showcases by Title

Results Per Page

Sort Options