Research

I am a Research Scientist in the On-Device AI team, at Facebook Reality Labs. Prior to joining Facebook, I had the privilege to be part of the Creative Intelligence Lab, at Adobe Research. I spent eight memorable years as Intern, PhD and Post-Doctoral Researcher at Disney Research Zurich, in the Imaging and Video Processing Group. I obtained my PhD in 2017 from ETHZ. My research lies at the intersection of Computer Graphics, Computer Vision and Machine Learning. 

Selected Publications

Shape Adaptor: A Learnable Resizing Module

Shikun Liu, Zhe Lin, Yilin Wang, Jianming Zhang, Federico Perazzi, Edward Johns

ECCV 2020 , Virtual

Pdf ArXiv BibTex Code
Scene Scale Estimation from Single Image in the Wild

Rui Zhu, X. Yang, Y. Hold-Geoffroy, F. Perazzi, J. Eisenmann, K. Sunkavalli, M. Chandraker

ECCV 2020 , Virtual

Pdf ArXiv
Basis Prediction Networks for Effective Burst Denoising with Large Kernels

Zhihao Xia, Federico Perazzi, Michael Gharbi, Kalyan Sunkavalli, Ayan Chakrabarti

CVPR 2020 , Seattle , Washington

Pdf ArXiv BibTex Project Page Video
Temporally Distributed Networks for Fast Video Segmentation

Ping Hu, Fabian Caba Heilbron, Oliver Wang, Zhe Lin, Stan Sclaroff, Federico Perazzi

CVPR 2020 , Seattle , Washington

Pdf ArXiv BibTex Project Page Code Poster
Active Speakers in Context

J. C. Leon, F. Caba Heilbron, L. Mai, F. Perazzi, J.-Y. Lee, P. Arbelaez, B. Ghanem

CVPR 2020 , Seattle , Washington

Pdf ArXiv
Scaling Object Detection by Transferring Classification Weights

Jason Kuen, Federico Perazzi, Zhe Lin, Jianming Zhang, Yap-Pen Tan

ICCV (oral) 2019 , Seoul , South Korea

Pdf ArXiv Code
Synthetic to Real Translation Via Explicit Image Disentanglement

Sai Bi, Kalyan Sunkavalli, Federico Perazzi, Eli Shechtman, Vladimir Kim, Ravi Ramamoorthi

ICCV 2019 , Seoul , South Korea

Pdf ArXiv BibTex
Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes

Chaoyang Wang, Simon Lucey, Federico Perazzi, Oliver Wang

3DV 2019 , Quebec City , Canada

Pdf ArXiv BibTex
On Regularized Losses for Weakly-supervised CNN Segmentation

M. Tang, F. Perazzi, A. Djelouah, I. B. Ayed, C. Schroers, Y. Boykov

ECCV 2018 , Munich , Germany

Pdf ArXiv BibTex Code
Normalized Cut Loss for Weakly-supervised CNN Segmentation

M. Tang, A. Djelouah, F. Perazzi, Y. Boykov, C. Schroers

CVPR 2018 , Salt Lake City , Utah

Pdf ArXiv BibTex Code
A Fully Progressive Approach to Single-Image Super-Resolution

Y. Wang, F. Perazzi, B. McWilliams, A. and O. Sorkine-Hornung, C. Schroers

CVPRW 2018 , Salt Lake City , Utah

Pdf ArXiv BibTex Project Page Code Video
Learning Video Object Segmentation From Static Images

F. Perazzi*, A. Khoreva*, R. Benenson, B. Schiele, A. Sorkine-Hornung

CVPR 2017 , Honolulu , Hawaii

Pdf ArXiv BibTex Project Page Poster
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation

F. Perazzi, J. Pont-Tuset, B. McWilliams, L. Van Gool, M. Gross, A. Sorkine-Hornung

CVPR 2016 , Las Vegas , Nevada

Pdf BibTex Project Page Code Poster
Bilateral Space Video Segmentation

Nicolas Märki, Federico Perazzi, Oliver Wang, Alexander Sorkine-Hornung

CVPR 2016 , Las Vegas , Nevada

Pdf BibTex Project Page Code Poster
Fully Connected Object Proposals for Video Segmentation

Federico Perazzi, Oliver Wang, Markus Gross, Alexander Sorkine-Hornung

ICCV 2015 , Santiago , Chile

Pdf BibTex Project Page Poster
Efficient Salient Foreground Detection for Images and Video using Fiedler Vectors

Federico Perazzi, Olga Sorkine-Hornung, Alexander Sorkine-Hornung

Eurographics WICED 2015 , Zurich , Switzerland

Pdf BibTex Project Page
Panoramic Video from Unstructured Camera Arrays

F. Perazzi, A. Sorkine-Hornung, H. Zimmer, P. Kaufmann, O. Wang, S. Watson, M. Gross

Eurographics 2015 , Zurich , Switzerland

Pdf BibTex Project Page Data Video
Non-Polynomial Galerkin Projection on Deforming Meshes

M. Stanton, Y. Sheng, M. Wicke, F. Perazzi, A. Yuen, S. Narasimhan, A. Treuille

SIGGRAPH 2013 , Anaheim , California

Pdf BibTex Project Page Video
Saliency Filters: Contrast Based Filtering for Salient Region Detection

Federico Perazzi, Philipp Krähenbühl, Yael Pritch and Alexander Hornung

CVPR 2012 , Providence , Rhode Island

Pdf BibTex Project Page Code Data Poster

Workshops

The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation

S. Caelles, J. Pont-Tuset, F. Perazzi, A. Montes, K.-K. Maninis, L. Van Gool

CVPRW 2019 , Long Beach , California

Pdf ArXiv BibTex Project Page Code Data
The 2018 DAVIS Challenge on Video Object Segmentation

S. Caelles, A. Montes, K.-K. Maninis, Y. Chen, L. Van Gool, F. Perazzi, J. Pont-Tuset

CVPRW 2018 , Salt-Lake City , Utah

Pdf ArXiv BibTex Project Page Code Data
The 2017 DAVIS Challenge on Video Object Segmentation

J. Pont-Tuset, F. Perazzi, S. Caelles, P. Arbeláez, A. Sorkine-Hornung, L. Van Gool

CVPRW 2017 , Honolulu , Hawaii

Pdf ArXiv BibTex Project Page Code Data

Patents

Teaching