activity
20182022
most citedRecovering Geometric Information with Learned Texture Perturbations

3 citations · 3 across the 4 of their papers we have counts for

collaborators

12 papers

cs.CV2022

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…

cs.LG2022

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…

cs.CV2020

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…

cs.CV20203 cited

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…

physics.comp-ph2019

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…

cs.CV2019

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…