I am a post-doctoral researcher at FAIR, and Stanford University; working under Prof. Jitendra Malik and Prof. Leonidas Guibas. Previously, I was a post-doc at the Technion and a research intern at Google, Intel and Microsoft Research. I received my PhD from Tel-Aviv University, where I was advised by Prof. Alex Bronstein. I received my B.Sc. in Physics and Mathematics from the Hebrew University under the auspices of “Talpiot”.

My research interests include: 3D deep learning, computational shape analysis and representation learning.

Honors & Awards

  • Best Paper Award Nominee, ICCV (2019)
  • Best Paper Award, ICLR LLD workshop (2019)
  • Outstanding Reviewer, Elsevier (2017)
  • Best Paper Award, Symposium on Geometry Processing (SGP) (2016)
  • Weinstein prize for graduate studies, Tel-Aviv University (2015)

Stanford Advisors

All Publications

  • ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes Qi, C., Chen, X., Litany, O., Guibas, L. 2020
  • Class-Aware Fully Convolutional Gaussian and Poisson Denoising IEEE TRANSACTIONS ON IMAGE PROCESSING Remez, T., Litany, O., Giryes, R., Bronstein, A. M. 2018; 27 (11): 5707–22


    We propose a fully-convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state-of-the-art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts performance, enhances textures and reduces artifacts.

    View details for DOI 10.1109/TIP.2018.2859044

    View details for Web of Science ID 000443702900006

    View details for PubMedID 30040645

  • Deformable Shape Completion with Graph Convolutional Autoencoders Litany, O., Bronstein, A., Bronstein, M., Makadia, A., IEEE IEEE. 2018: 1886–95
  • Fully Spectral Partial Shape Matching COMPUTER GRAPHICS FORUM Litany, O., Rodola, E., Bronstein, A. M., Bronstein, M. M. 2017; 36 (2): 247–58

    View details for DOI 10.1111/cgf.13123

    View details for Web of Science ID 000404474000024

  • ASIST: Automatic semantically invariant scene transformation COMPUTER VISION AND IMAGE UNDERSTANDING Litany, O., Remez, T., Freedman, D., Shapira, L., Bronstein, A., Gal, R. 2017; 157: 284–99
  • Deep Functional Maps: Structured Prediction for Dense Shape Correspondence Litany, O., Remez, T., Rodola, E., Bronstein, A., Bronstein, M., IEEE IEEE. 2017: 5660–68
  • Efficient Deformable Shape Correspondence via Kernel Matching Vestner, M., Laehner, Z., Boyarski, A., Litany, O., Slossberg, R., Remez, T., Rodola, E., Bronstein, A., Bronstein, M., Kimmel, R., Cremers, D., IEEE IEEE. 2017: 517–26
  • Non-Rigid Puzzles Litany, O., Rodola, E., Bronstein, A. M., Bronstein, M. M., Cremers, D. WILEY. 2016: 135–43

    View details for DOI 10.1111/cgf.12970

    View details for Web of Science ID 000383444500014

  • A Picture is Worth a Billion Bits: Real-time Image Reconstruction from Dense Binary Threshold Pixels Remez, T., Litany, O., Bronstein, A., IEEE IEEE. 2016: 72–80
  • Putting the Pieces Together: Regularized Multi-part Shape Matching Litany, O., Bronstein, A. M., Bronstein, M. M., Fusiello, A., Murino, Cucchiara, R. SPRINGER-VERLAG BERLIN. 2012: 1–11