Search Results for author: Ronald Fedkiw

Found 13 papers, 0 papers with code

Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Maps

no code implementations27 Nov 2023 Jane Wu, Diego Thomas, Ronald Fedkiw

We present a novel deep learning-based approach to the 3D reconstruction of clothed humans using weak supervision via 2D normal maps.

3D Reconstruction

Addressing Discontinuous Root-Finding for Subsequent Differentiability in Machine Learning, Inverse Problems, and Control

no code implementations21 Jun 2023 Daniel Johnson, Ronald Fedkiw

There are many physical processes that have inherent discontinuities in their mathematical formulations.

Software-based Automatic Differentiation is Flawed

no code implementations5 May 2023 Daniel Johnson, Trevor Maxfield, Yongxu Jin, Ronald Fedkiw

Various software efforts embrace the idea that object oriented programming enables a convenient implementation of the chain rule, facilitating so-called automatic differentiation via backpropagation.

Analytically Integratable Zero-restlength Springs for Capturing Dynamic Modes unrepresented by Quasistatic Neural Networks

no code implementations25 Jan 2022 Yongxu Jin, Yushan Han, Zhenglin Geng, Joseph Teran, Ronald Fedkiw

We present a novel paradigm for modeling certain types of dynamic simulation in real-time with the aid of neural networks.

Skinning a Parameterization of Three-Dimensional Space for Neural Network Cloth

no code implementations8 Jun 2020 Jane Wu, Zhenglin Geng, Hui Zhou, Ronald Fedkiw

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 underlying body.

Recovering Geometric Information with Learned Texture Perturbations

no code implementations20 Jan 2020 Jane Wu, Yongxu Jin, Zhenglin Geng, Hui Zhou, Ronald Fedkiw

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-frequency information present in the training data.

Coercing Machine Learning to Output Physically Accurate Results

no code implementations21 Oct 2019 Zhenglin Geng, Dan Johnson, Ronald Fedkiw

Although one could project the output of a network into a physically feasible region, such a postprocess is not captured by the energy function minimized when training the network; thus, the final projected result could incorrectly deviate quite far from the training data.

BIG-bench Machine Learning

Local Geometric Indexing of High Resolution Data for Facial Reconstruction from Sparse Markers

no code implementations1 Mar 2019 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 smoothness constraints.

Physical Simulations

Three Dimensional Reconstruction of Botanical Trees with Simulatable Geometry

no code implementations20 Dec 2018 Ed Quigley, Winnie Lin, Yilin Zhu, Ronald Fedkiw

We tackle the challenging problem of creating full and accurate three dimensional reconstructions of botanical trees with the topological and geometric accuracy required for subsequent physical simulation, e. g. in response to wind forces.

Deep Energies for Estimating Three-Dimensional Facial Pose and Expression

no code implementations7 Dec 2018 Michael Bao, Jane Wu, Xinwei Yao, Ronald Fedkiw

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 rotoscope curves hand-drawn on the image.

Improved Search Strategies with Application to Estimating Facial Blendshape Parameters

no code implementations7 Dec 2018 Michael Bao, David Hyde, Xinru Hua, Ronald Fedkiw

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 terms added to the energy functional.

High-Quality Face Capture Using Anatomical Muscles

no code implementations CVPR 2019 Michael Bao, Matthew Cong, Stéphane Grabli, Ronald Fedkiw

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 differentiability has limited their impact.

Vocal Bursts Intensity Prediction

A Pixel-Based Framework for Data-Driven Clothing

no code implementations3 Dec 2018 Ning Jin, Yilin Zhu, Zhenglin Geng, Ronald Fedkiw

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 as an RGB image in a two dimensional pattern space.

Cannot find the paper you are looking for? You can Submit a new open access paper.