Ming-Yu Liu is a principal research scientist at NVIDIA Research. Before joining NVIDIA in 2016, he was a principal research scientist at Mitsubishi Electric Research Labs (MERL). He earned his Ph.D. from the Department of Electrical and Computer Engineering at the University of Maryland College Park in 2012, advised by Prof. Rama Chellappa. He received the R&D 100 Award for his robotic bin picking work in 2014. His street scene understanding paper was in the best paper finalist in the 2015 Robotics Science and System (RSS) conference. In CVPR 2018, he won the 1st place in both the domain adaptation for semantic segmentation competition and the optical flow estimation competition. In the recent years, his research focus is on generative image modeling. His work in this space include pix2pixHD, vid2vid, GauGAN/SPADE, UNIT, MUNIT, and FUNIT. His generative model works have been covered in various media outlets including the New York Times. His research goal is to enable machines human-like imagination capabilities.

Research Focus

FUNIT: Few-shot Unsupervised Image-to-Image Translation (arXiv 2019)

SPADE: Semantic Image Synthesis with Spatially-Adaptive Normalization (CVPR 2019, Siggraph Real Time Live 2019)

vid2vid: Video-to-Video Synthesis (NeurIPS 2018)

MUNIT: Multimodal unsupervised image-to-image translation (ECCV 2018)

A Closed-form Solution to Photorealistic Image Stylization (ECCV 2018)

High-res image synthesis and semantic manipulation (CVPR 2018)

Decomposing Motion and Content for Video Generation (CVPR 2018)

Unsupervised image-to-image translation Network (NeurIPS 2017)

Coupled GAN
Coupled Generative Adversarial Networks (NeurIPS 2016)


Participated Peer Review

  • Conference reviewer: CVPR, ICCV, ECCV, NIPS, ICML, ICLR

  • Journal reviewer: TPAMI, IJCV, TIP, TMM, CVIU

  • Journal guess editor: IJCV, CVIU

  • Area chair: ICCV, BMVC, WACV

Co-hosted Tutorial

  • ICIP 2019 Tutorial: Image-to-Image Translation

  • CVPR 2019 Tutorial: Deep Learning for Content Creation

  • CVPR 2017 Tutorial: Theory and Applications of Generative Adversarial Networks, [Site]

  • ACCV 2016 Tutorial: Deep Learning for Vision Guided Language Generation and Image Generation, [Site]

Co-hosted Workshop

  • CVPR 2019 Workshop: 4th New Trends in Image Restoration and Enhancement workshop and challenges

  • CVPR 2019 Workshop: AI City Challenge, [Site]

  • CVPR 2018 Workshop: AI City Challenge, [Site]