Papers, Patents,


    I am AI: AI-driven Digital Avatar Made Easy
    Ming-Yu Liu, Koki Nagano, Yeongho Seol, Rafael Valle, Jaewoo Seo, Ting-Chun Wang, Arun Mallya, Sameh Khamis, Wei Ping, Rohan Badlani, Kevin J. Shih, Bryan Catanzaro, Simon Yuen, Jan Kautz
    SIGGRAPH RTL 2021 (Best-in-Show)
    Dancing to Music
    Hsin-Ying Lee, Xiaodong Yang, Ming-Yu Liu, Ting-Chun Wang, Yu-Ding Lu, Ming-Hsuan Yang, Jan Kautz
    NeurIPS 2019
    The 2018 NVIDIA AI City Challenge
    Milind Naphade, Ming-Ching Chang, Anuj Sharma, David C. Anastasiu, Vamsi Jagarlamudi, Pranamesh Chakraborty, Tingting Huang, Shuo Wang, Ming-Yu Liu, Rama Chellappa, Jenq-Neng Hwang, and Siwei Lyu
    CVPR 2018 (Workshop)

Awarded Patents

    My NVIDIA patents.

  • US 11,082,720: Using residual video data resulting from a compression of original video data to improve a decompression of the original video data

  • US 11,017,556: Iterative spatio-temporal action detection in video

  • US 10,984,286: Domain stylization using a neural network model

  • US 10,922,792: Guided hallucination for missing image content using a neural network

  • US 10,872,399: Photorealistic image stylization using a neural network model

  • US 10,789,678: Superpixel sampling networks

  • US 10,748,036: Training a neural network to predict superpixels using segmentation-aware affinity loss

  • US 10,595,039: System and method for content and motion controlled action video generation

  • US 10,593,020: Unsupervised learning approach for video deblurring

  • US 10,424,069: System and method for optical flow estimation

  • My MERL patents.

  • US 9,989,964: System and Method for Controlling Vehicle Using Neural Network

  • US 9,971,958: Method and System for Generating Multimodal Digital Images

  • US 9,811,756: Method for Labeling Images of Street Scenes

  • US 9,805,294: Method for Denoising Time-of-Flight Range Images

  • US 9,704,257: System and method for semantic segmentation using Gaussian random field network

  • US 9,633,274: Method and system for denoising images using deep Gaussian conditional random field network

  • US 9,558,268: Method for semantically labeling an image of a scene using recursive context propagation

  • US 9,280,827: Method for determining object poses using Weighted Features

  • US 9,195,904: Method for detecting objects in stereo images

  • US 8,983,177: Method for increasing resolutions of depth images

  • US 8,908,913: Voting-based pose estimation for 3D sensors

  • US 8,428,363: Method for segmenting images using superpixels and entropy rate clustering