SCA 2020: Showcases

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632938

Browse

Browsing SCA 2020: Showcases by Subject "Computing methodologies"

Now showing 1 - 4 of 4
  • Thumbnail Image
    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, 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.
  • Thumbnail Image
    Item
    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.
  • Thumbnail Image
    Item
    Negative Jacobian Free Simulations Using Principal Stretches
    (The Eurographics Association, 2020) Francu, Mihail; Holden, Daniel
    Finite element (FE) simulations are prone to encountering negative Jacobians during the solving process. If nothing is done, the simulation can be brought to a halt, result in inverted elements or have undetermined behavior. We propose a solution that uses principal stretches as slack variables in a constrained minimization formulation and enforce them to always be positive. We show that our approach can never hit inverted configurations, thus being suitable for applications where inversion cannot be tolerated. We implement the method in 2D and show that it outperforms standard FE methods in stressful scenarios.
  • Thumbnail Image
    Item
    ZooBuilder: 2D and 3D Pose Estimation for Quadrupeds Using Synthetic Data
    (The Eurographics Association, 2020) Fangbemi, Abassin Sourou; Lu, Yi Fei; Xu, Maoyuan; Luo, Xiaowu; Rolland, Alexis; Raissi, Chedy; Holden, Daniel
    This work introduces a novel strategy for generating synthetic training data for 2D and 3D pose estimation of animals using keyframe animations. With the objective to automate the process of creating animations for wildlife, we train several 2D and 3D pose estimation models with synthetic data, and put in place an end-to-end pipeline called ZooBuilder. The pipeline takes as input a video of an animal in the wild, and generates the corresponding 2D and 3D coordinates for each joint of the animal's skeleton. With this approach, we produce motion capture data that can be used to create animations for wildlife.