Ming-Yu Liu is a senior research scientist at NVIDIA Research. Before joining NVIDIA Research, he was a principal research scientist at Mitsubishi Electric Research Labs (MERL). He received his Ph.D. from the Department of Electrical and Computer Engineering at the University of Maryland College Park in 2012. The object pose estimation algorithm he developed at MERL was a major component of a commercial vision-based robotic bin-picking system, which was awarded the 100 most innovative technology products of the year by the R&D magazine in 2014. His street scene understanding paper was a best paper finalist in the 2015 Robotics Science and System (RSS) conference. Recently, his research focus shifted to generative models for image understanding and generation. His goal is to enable machines superhuman-like imagination capabilities.

Check out my new code release in GitHub. Follow me on Twitter Twitter

Recent Research Focus

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

FastPhotoStyle Transfer style of a real photo to another real photo (ECCV 2018)


pix2pixHD High-res image synthesis and semantic manipulation (CVPR 2018)


CoupledGAN Unsupervised image-to-image translation (NIPS 2016, NIPS 2017)
Left: input; right: machine-generated


MoCoGAN for video generation (CVPR 2018)


Other Research


Awards


Service

  • Reviewer: NIPS, ICML, ICLR, CVPR, ICCV, ECCV, IEEE TPAMI, IEEE TIP, IEEE SPL, CVIU, NSF proposal

  • Area Chair: WACV'17, BMVC'18


Media