 
  
    Associate Professor, Department of Computer Science
    University College London
    i.kokkinos@ucl.ac.uk
    [CV] 
    [Google Scholar] 
    [LinkedIn]
  
I am an Associate Professor of Computer Science at University College London, working at the intersection of computer vision and deep learning, with an emphasis on 3D human understanding and weakly-supervised learning of 3D geometric representations.
  I am particularly interested in bridging academic research and real-world applications and have held multiple roles in industry:
  From 2016 to 2018, I was a Research Scientist at Facebook AI Research (FAIR). 
  From 2018 to 2020, I was co-founder and CEO of Ariel AI, a startup for real-time, full-body 3D reconstruction for augmented reality (AR) that was acquired by Snap in 2020. 
  From 2020 to 2024, I  led the Human3D team in Snap, helping deliver full-body AR experiences to hundreds of millions of Snapchat users. 
  
MeshPose: Unifying DensePose and 3D Body Mesh reconstruction
  Eric-Tuan Le, Antonis Kakolyris, Petros Koutras, Himmy Tam, Efstratios Skordos, Riza Alp Guler, George Papandreou, Iasonas Kokkinos
  CVPR, 2024
  [Project Page]
  
StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN
  Eric-Tuan Le, Edward Batrum, Iasonas Kokkinos
  ICLR, 2023
  [Project Page]
  
To The Point: Correspondence-driven monocular 3D category reconstruction
  Filippos Kokkinos, Iasonas Kokkinos
  NeurIPS, 2021
  [Project Page]
  
Learning monocular 3D reconstruction of articulated categories from motion
  Filippos Kokkinos, Iasonas Kokkinos
  CVPR, 2021
  [Project Page]
  
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
  Dominik Kulon, Riza Alp Güler, Iasonas Kokkinos, Michael Bronstein, Stefanos Zafeiriou
  CVPR 2020 (Oral, Best Paper Shortlist)
  [Video]
  
HoloPose: Holistic 3D Human Reconstruction In-The-Wild
  Riza Alp Guler, Iasonas Kokkinos
  CVPR, 2019 (Oral)
  [Video]
  
DensePose: Dense Human Pose Estimation In The Wild
  Riza Alp Güler, Natalia Neverova, Iasonas Kokkinos
  CVPR, 2018 (Oral)
  [Video]
  
UberNet: Training a 'Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory
  Iasonas Kokkinos
  CVPR, 2017 (Oral)
  [talk] [Video]
  
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
  Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille
  IEEE Transactions on PAMI, 2017
[