CVPR 2020

Facebook at the 2020 Conference on Computer Vision and Pattern Recognition

Facebook is thrilled to contribute to CVPR 2020. This year, we will present over 35 papers at the conference and participate in more than 35 workshops and tutorials. These results come from across Facebook’s diverse research teams working in AI, AR/VR, computational photography, robotics, and many more. We seek to advance the state-of-the-art in computer vision through fundamental and applied research in open collaboration with CVPR’s dynamic scientific community. Our products empower more than 3 billion people around the world to share ideas, offer support, and make a difference. Research is at the core of this mission and our teams focus on projects we believe will have the most positive impact on people and society. Explore this page for more details on our research, scheduled events and collaboration, and career opportunities.

View facebook research at CVPR

The Lower-Power Vision Challenge

PyTorch researchers and developers are invited to join the 2020 CVPR Lower-Power Vision Challenge (LPVC) — Online Track for UAV video. The goal of this challenge is to build a system that can discover and recognize characters in video captured by an unmanned aerial vehicle (UAV) accurately using PyTorch Mobile and Raspberry Pi 3B+. Online submission is open July 1, 2020 to July 31, 2020.


Facebook Publications At CVPR 2020

See All

June 11, 2020

Self-Supervised Learning of Pretext-Invariant Representations

Ishan Misra, Laurens van der Maaten

June 11, 2020

12-in-1: Multi-Task Vision and Language Representation Learning

Jiasen Lu, Vedanuj Goswami, Marcus Rohrbach, Devi Parikh, Stefan Lee

June 11, 2020

DLWL: Improving Detection for Lowshot classes with Weakly Labelled data

Vignesh Ramanathan, Rui Wang, Dhruv Mahajan

April 7, 2020

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

Shunsuke Saito, Tomas Simon, Jason Saragih, Hanbyul Joo

May 26, 2020

Epipolar Transformers

Yihui He, Rui Yan, Katerina Fragkiadaki, Shoou-I Yu

June 11, 2020

VPLNet: Deep Single View Normal Estimation with Vanishing Points and Lines

Rui Wang, David Geraghty, Kevin Matzen, Richard Szeliski, Jan-Michael Frahm