Program

Workshop Schedule

20th June 2022 - 1:00pm - 5:00pm (All times US Central (CST))

1:00 - 1:03 pm

Introduction and WoodScape Challenge Overview

1:03 - 1:15 pm

WoodScape Object Detection Challenge Winner

Invited Speaker Talk: 25 mins and 5 mins questions

1:15 - 1:45 pm

Keynote: Journey of Kannala-Brandt model
Prof. Juho Kannala (Aalto University, Finland)

1:45 - 2:15 pm

Keynote: Omnidirectional depth prediction for cars
Dr.
Vitor Guizilini (Toyota Research Institute, California)

2:15 - 2:45 pm

Keynote: Efficient Deep Learning on the edge and BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation
Prof. Song Han (MIT, Boston)

2:45 - 3:15 pm

Keynote: Extreme Panoramic Indoor Reconstruction
Prof. Yasutaka Furukawa (Simon Fraser University, Canada)

15 MINUTE BREAK

Author Talk: 9 mins and 1 min questions

3:30 - 3:40 pm

A New Non-central Model for Fisheye Calibration
Author: Radka Tezaur, Intel Corp. (In-person)

3:40 - 3:50 pm

HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model
Author: Md Baharul Islam, Department of Computer Engineering, Bahcesehir University (In-person)

3:50 - 4:00 pm

Photometric Visual Gyroscope for Full-View Spherical Camera
Author: Antoine André, Université de Picardie Jules Verne (In-person)

4:10 - 4:20 pm

Pose Estimation for Two-View Panoramas based on Keypoint Matching: a Comparative Study and Critical Analysis
Author: Jeffri Murrugarra, Federal University of Rio Grande do Sul (In-person)

4:20 - 4:30 pm

Best Paper Award: SPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecasting
Author: Quentin Paletta, University of Cambridge (Virtual)

4:30 - 4:40 pm

Rethinking Supervised Depth Estimation for 360 Panoramic Imagery
A
uthor: Lu He, Tencent America (Virtual)

4:40 - 4:50 pm

3D Room Layout Recovery Generalizing across Manhattan and Non-Manhattan Worlds
Author: Haijing Jia, Ricoh Software Research Center Beijing (Virtual)

4:50 - 5:00 pm

Casual Radiance Capture and Synthesis for Indoor Scenes
Author: Pulkit Gera, CVIT, International Institute of Information Technology, Hyderabad (Virtual)

CLOSING NOTES