Federico Perazzi

Research Scientist

San Francisco

Federico is a Research Scientist in the Creative Intelligence Lab. Prior to joining Adobe Research, Federico spent eight years as Intern, PhD and Post-Doctoral Researcher at Disney Research. He obtained the PhD in 2017 from ETHZ. He received an MSc in Entertainment Technology from Carnegie Mellon University in 2010 and an MSc in Computer Science from ETHZ in 2013.

Federico’s current research investigates novel methods for: image enhancement, semantic image understanding (classification, detection and segmentation) human pose and unsupervised depth estimation.

For more information, please visit his personal page at: fperazzi.github.io


Scaling Object Detection by Transferring Classification Weights

Kuen, J., Perazzi, F., Lin, Z., Zhang, J., Tan, Y. (Nov. 1, 2019)

ICCV (oral, acceptance rate ~5.0%)

Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement

Bi, S., Sunkavalli, K., Perazzi, F., Shechtman, E., Kim, V., Ramamoorthi, R. (Oct. 29, 2019)

International Conference on Computer Vision (ICCV'19)

Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes

Wang, C., Lucey, S., Perazzi, F., Wang, O. (Sep. 27, 2019)

3DV 2019

On Regularized Losses for Weakly-supervised CNN Segmentation

Tang, M., Perazzi, F., Djelouah, A., Ayed, I., Schroers, C., Boykon, Y. (Jun. 22, 2018)

ECCV 2018