Publications

  • Geometry Processing using Neural Fields
    Guandao Yang, Serge Belongie, Bharath Hariharan, Vladlen Koltun
    In NeurIPS, 2021
    TLDR : Can we manipulate shapes by solely manipulating a neural implicit field?
    pdf    bibtex
  • Extreme Rotation Estimation using Dense Correlation Volumes
    Ruojin Cai, Hadar Averbuch-Elor, Bharath Hariharan, Noah Snavely
    In CVPR, 2021
    TLDR : Can we estimate relative camera pose between two views which don't overlap at all?
    pdf    project page    bibtex
  • Stay Positive: Non-Negative Image Synthesis for Augmented Reality
    Katie Luo, Guandao Yang, Wenqi Xian, Harald Haraldsson, Bharath Hariharan, Serge Belongie
    In CVPR, 2021 (Oral)
    TLDR : How do we project a synthetic world into a real one by only adding light?
    pdf    project page    bibtex
  • Wasserstein Distances for Stereo Depth Estimation
    Divyansh Garg, Yan Wang, Bharath Hariharan, Mark Campbell, Kilian Q Weinberger, Wei-Lun Chao
    In NeurIPS, 2020 (Oral)
    TLDR : A new loss function for depth estimation that compares distributions of predicted depth with the ground truth
    pdf    project page    bibtex
  • Learning Gradient Fields for Shape Generation
    Ruojin Cai, Guandao Yang, Hadar Averbuch-Elor, Zekun Hao, Serge Belongie, Noah Snavely, Bharath Hariharan
    In ECCV, 2020 (Spotlight)
    TLDR : A new way of representing shapes by using neural networks to model the gradient of the probability distribution of surface points.
    pdf    project page    bibtex
  • Learning Feature Descriptors using Camera Pose Supervision
    Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, Noah Snavely
    In ECCV, 2020 (Oral)
    TLDR : We learn neural network-based feature descriptors solely from camera pose without any ground truth correspondences
    pdf    supp    project page    bibtex
  • PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
    Guandao Yang*, Xun Huang*, Zekun Hao, Ming-Yu Liu, Serge Belongie, Bharath Hariharan
    In ICCV, 2019 (Oral)
    TLDR : We consider point clouds as distributions of surface points, which we model using a variant of neural ODEs
    pdf    project page    bibtex
  • Few-Shot Generalization for Single-Image 3D Reconstruction via Prior
    Bram Wallace, Bharath Hariharan
    In ICCV, 2019
    TLDR : A single-view 3D reconstruction system that explicitly leverages the average category shape, and can thus generalize to new classes without training
    pdf    bibtex
  • Learning Single-View 3D Reconstruction with Limited Pose Supervision
    Guandao Yang, Yin Cui, Serge Belongie, Bharath Hariharan
    In ECCV, 2018
    TLDR : We explore many ways of reducing the need for ground truth annotations for training 3D reconstruction systems
    pdf    bibtex