Large Scale Computer Vision for Remote Sensing Imagery
June 14, 2020, Seattle, Washington
in conjunction with the Computer Vision and Pattern Recognition (CVPR) 2020 Conference
Program

CVPR'20 and therefore also EarthVision'20 will be fully virtual. For regular papers, we follow the CVPR schedule: Each paper is presented by a pre-recorded video that is accessible throughout the WS. Questions and comments to the authors can be made via a text-based chat (also available throughout the WS) as well as during two live video sessions 12h apart. The times below are local times for Seattle of the first round. The second round starts exactly 12h later.

The opening and closing sessions as well as most of the keynotes will be live, i.e. there is no prerecorded video but a live virtual session for the presentation as well as to interact with the presenters. The keynotes will be given only during the first round, i.e. there is no second live presentation in the second round after 12h. One keynote will be given as video with no Q&A session.

All material will be made available to the registered attendees via a webpage administered by CVPR. Only the session for the SpaceNet6 challenge will be hosted externally.

08:30 - 08:40 Welcome


08:45 - 09:25 Keynote 1


Markus Reichstein, Max Planck Institute, Germany

(Live talk + Q&A, only in the first round)


09:30 - 10:30 Q&A Session 1 - Applied Deep Learning

(Video + live Q&A, both rounds)


Corinne Stucker (ETH Zurich); Konrad Schindler (ETH Zurich)

ResDepth: Learned Residual Stereo Reconstruction


Rasha Alshehhi (NYU)

Deep Regression for Imaging Solar Magnetograms using Pyramid Generative Adversarial Networks


Armin Hadzic (University of Kentucky); Hunter Blanton (University of Kentucky); Weilian Song (Simon Fraser University); Mei Chen (University of Kentucky); Scott Workman (DZYNE Technologies); Nathan Jacobs (University of Kentucky)

RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery


Nina Varney (University of Dayton); Vijayan K Asari (University of Dayton); Quinn Graehling (University of Dayton)

DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentation


Weikai Tan (University of Waterloo); Li Jonathan (Xiamen University)

Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways


Derrick J Bonafilia (Cloud to Street); Tyler Anderson (Cloud to Street); Erica Issenberg (Cloud to Street); Beth Tellman (Cloud to Street)

Sen1Floods11: a georeferenced dataset to train and test deep learning flood algorithms for Sentinel-1


10:30 - 11:00 Break


11:00 - 11:35 Keynote 2


Sveinung Loekken, ESA

Title: The Contours of a trillion-pixel Digital Twin Earth

(Live talk + Q&A, only in the first round)


11:40 - 12:40 SpaceNet 6 Challenge


12:40 - 14:00 Break


14:00 - 14:30 Keynote 3


Serge Belongie, Cornell Tech., USA

Title: A New Workflow for Collaborative Machine Learning

Research in Biodiversity

(Live talk + Q&A, only in the first round)


14:35 - 15:45 Q&A Session 2 - Synthesis and Semantic Analysis

(Video + live Q&A, both rounds)


Changlin Li (UNCC Vision lab); Taojiannan Yang (UNC Charlotte); Sijie Zhu (University of North Carolina at Charlotte); Chen Chen (University of North Carolina at Charlotte); Shanyue Guan (East Carolina University)

Density Map Guided Object Detection in Aerial Images


Onur Tasar (INRIA); Yuliya Tarabalka (Inria Sophia-Antipolis); Alain Giros (CNES); Pierre Alliez (INRIA Sophie-Antipolis, France); Sébastien Clerc (ACRI-ST)

StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization


Saqib Ali Khan (School of Electrical Engineering and Computer Sciences, NUST); Yilei Shi (Technical University of Munich); Muhammad Shehzad (School of Electrical Engineering and Computer Sciences, NUST); Xiaoxiang Zhu (Technical University of Munich (TUM); German Aerospace Center (DLR))

FGCN: Deep Feature-based Graph Convolutional Network for Semantic Segmentation of Urban 3D Point Clouds


Marc Rußwurm (Technical University of Munich); Sherrie Wang (Stanford University); Marco Körner (Technical University of Munich); David Lobell (Stanford University)

Meta-Learning for Few-Shot Land Cover Classification


Litu Rout (Space Applications Centre, Indian Space Research Organisation); Indranil Misra (ISRO); Manthira Moorthi S (ISRO); Debajyoti Dhar (ISRO)

S2A: Wasserstein GAN with Spatio-Spectral Laplacian Attention for Multi-Spectral Band Synthesis


Litu Rout (Space Applications Centre, Indian Space Research Organisation); Saumyaa Shah (Nirma University); Manthira Moorthi S (ISRO); Debajyoti Dhar (ISRO)

Monte-Carlo Siamese Policy on Actor for Satellite Image Super Resolution


Md Rifat Arefin (Mila); Vincent Michalski (Mila); Pierre-Luc St-Charles (MILA); Alfredo Kalaitzis (Element AI); Sookyung Kim (Lawrence Livermore National Laboratory); Samira Ebrahimi Kahou (McGill/Mila); Yoshua Bengio (Mila)

Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent Networks


15:45 - 16:00 Break


16:00 - 16:40 Keynote 4


Maros Blaha, Apple

Title: Towards Large-Scale Remote Sensing of Human Habitats

(Video, no Q&A)


16:40 - 17:00 Awards & Closing


(Live, both rounds)



Latest news
  • May 28: The final program is now available.
  • May 28: EarthVision'20 will be fully virtual. We follow the CVPR schedule: Each paper is presented by a pre-recorded video that is accessible throughout the WS. Questions and comments to the authors can be made via a text-based chat as well as during two live video sessions 12h apart.
  • Apr 27: 14 accepted papers are listed.
  • Mar 23: We received a record number of 53 valid submissions. Which are now reviewed by more than 60 reviewers to ensure the highest quality!
  • Mar 13: We are excited to announce that Apple joins the Gold sponsors of EarthVision2020 after CosmiQ works, ESA (as Gold sponsors) and Kitware (as Bronze sponsor).
  • Mar 12: We are closely monitoring the developments around COVID-19 and its implications for EarthVision20. At the moment, CVPR20 and therefore EV20 are planned to take place maybe with changes to presentations (e.g. remotely) if necessary. We will announce any significant changes as soon as possible.
  • Feb 7: Workshop date is publicly announced to be Jun 14, 2020.
  • Jan 1: Submission system is open.
  • Nov 21: Challenge description online.
  • Nov 4: Website is open!
Sponsors
Affiliations