37 citations · 63 across the 13 of their papers we have counts for
16 papers
Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands
Sarah Jobalia, Yitong Deng, Carolyn Smith +1
We present a framework for understanding and generating feature rich hair strands. Drawing upon both scientific and cultural expertise, we define strand texture as the various dist…
Addressing Discontinuous Root-Finding for Subsequent Differentiability in Machine Learning, Inverse Problems, and Control
Daniel Johnson, Ronald Fedkiw
There are many physical processes that have inherent discontinuities in their mathematical formulations. This paper is motivated by the specific case of collisions between two rigi…
Software-based Automatic Differentiation is Flawed
Daniel Johnson, Trevor Maxfield, Yongxu Jin +1
Various software efforts embrace the idea that object oriented programming enables a convenient implementation of the chain rule, facilitating so-called automatic differentiation v…
Leveraging Deepfakes to Close the Domain Gap between Real and Synthetic Images in Facial Capture Pipelines
Winnie Lin, Yilin Zhu, Demi Guo +1
We propose an end-to-end pipeline for both building and tracking 3D facial models from personalized in-the-wild (cellphone, webcam, youtube clips, etc.) video data. First, we prese…
Analytically Integratable Zero-restlength Springs for Capturing Dynamic Modes unrepresented by Quasistatic Neural Networks
Yongxu Jin, Yushan Han, Zhenglin Geng +2
We present a novel paradigm for modeling certain types of dynamic simulation in real-time with the aid of neural networks. In order to significantly reduce the requirements on data…
A Robust Grid-Based Meshing Algorithm for Embedding Self-Intersecting Surfaces
Steven W. Gagniere, Yushan Han, Yizhou Chen +4
The creation of a volumetric mesh representing the interior of an input polygonal mesh is a common requirement in graphics and computational mechanics applications. Most mesh creat…
Skinning a Parameterization of Three-Dimensional Space for Neural Network Cloth
Jane Wu, Zhenglin Geng, Hui Zhou +1
We present a novel learning framework for cloth deformation by embedding virtual cloth into a tetrahedral mesh that parametrizes the volumetric region of air surrounding the underl…
Recovering Geometric Information with Learned Texture Perturbations
Jane Wu, Yongxu Jin, Zhenglin Geng +2
Regularization is used to avoid overfitting when training a neural network; unfortunately, this reduces the attainable level of detail hindering the ability to capture high-frequen…
Coercing Machine Learning to Output Physically Accurate Results
Zhenglin Geng, Dan Johnson, Ronald Fedkiw
Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data…
Local Geometric Indexing of High Resolution Data for Facial Reconstruction from Sparse Markers
Matthew Cong, Lana Lan, Ronald Fedkiw
When considering sparse motion capture marker data, one typically struggles to balance its overfitting via a high dimensional blendshape system versus underfitting caused by smooth…
A Robust Volume Conserving Method for Character-Water Interaction
Minjae Lee, David Hyde, Kevin Li +1
We propose a novel volume conserving framework for character-water interaction, using a novel volume-of-fluid solver on a skinned tetrahedral mesh, enabling the high degree of the…
Three Dimensional Reconstruction of Botanical Trees with Simulatable Geometry
Ed Quigley, Winnie Lin, Yilin Zhu +1
We tackle the challenging problem of creating full and accurate three dimensional reconstructions of botanical trees with the topological and geometric accuracy required for subseq…
Deep Energies for Estimating Three-Dimensional Facial Pose and Expression
Michael Bao, Jane Wu, Xinwei Yao +1
While much progress has been made in capturing high-quality facial performances using motion capture markers and shape-from-shading, high-end systems typically also rely on rotosco…
High-Quality Face Capture Using Anatomical Muscles
Michael Bao, Matthew Cong, Stéphane Grabli +1
Muscle-based systems have the potential to provide both anatomical accuracy and semantic interpretability as compared to blendshape models; however, a lack of expressivity and diff…
A Pixel-Based Framework for Data-Driven Clothing
Ning Jin, Yilin Zhu, Zhenglin Geng +1
With the aim of creating virtual cloth deformations more similar to real world clothing, we propose a new computational framework that recasts three dimensional cloth deformation a…
Improved Search Strategies with Application to Estimating Facial Blendshape Parameters
Michael Bao, David Hyde, Xinru Hua +1
It is well known that popular optimization techniques can lead to overfitting or even a lack of convergence altogether; thus, practitioners often utilize ad hoc regularization term…