3 papers
cs.CV2020
Data-driven Regularization via Racecar Training for Generalizing Neural Networks
You Xie, Nils Thuerey
We propose a novel training approach for improving the generalization in neural networks. We show that in contrast to regular constraints for orthogonality, our approach represents…
cs.GR2019
A Multi-Pass GAN for Fluid Flow Super-Resolution
Maximilian Werhahn, You Xie, Mengyu Chu +1
We propose a novel method to up-sample volumetric functions with generative neural networks using several orthogonal passes. Our method decomposes generative problems on Cartesian…
cs.CV2018
Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
Mengyu Chu, You Xie, Jonas Mayer +2
Our work explores temporal self-supervision for GAN-based video generation tasks. While adversarial training successfully yields generative models for a variety of areas, temporal…