We live in a world where location is the key for many activities, and computer vision plays a key role for answering the fundamental questions for location-based reasoning and mapping: (1) Where am I? (2) Where I am going? (3) How do I get there? The future world, not too far from our real life, would be full of autonomous robotics and AI agents: autonomous vehicles, autonomous taxis, autonomous delivery vans, autonomous drones, autonomous robotics etc. and location-based reasoning, especially mapping, has drawn a lot of attention from the computer vision community recently, both academia and industry.

The Vision Meets Mapping (VMM) Tutorial is an annual international event in conjunction with the annual Computer Vision and Pattern Recognition (CVPR) conference, which brings world class researchers together to present their latest development of mapping technologies using computer vision.

The first Vision Meets Mapping (VMM1) tutorial at CVPR 2019 in Long Beach had drawn over 200+ people to attend and was one of the few overly crowded and well-attended tutorials. We had gathered leading researchers/experts from HERE, Uber, AMap (AutoNavi/Alibaba), Mapillary to present their research work on outdoor mapping and the tutorials were well received by the computer vision community.

The 2nd Vision Meets Mapping (VMM2) tutorial at CVPR 2020 in Seattle (Virtual) had drawn over 100+ participants despite the challenges of virtual meeting format and schedule, and we had invited leading researchers/experts from Uber, TomTom, Mapillary, and Univ of Calgary to present their latest progress in outdoor mapping and were well received by the computer vision community.

The 3rd Vision Meets Mapping (VMM3) tutorial at CVPR 2021 was fully virtual, it attracts more than 100 participants despite the challenges of virtual meeting format and schedule, and we had invited leading researcher/experts from TomTom, Facebook, Waabi, Amap, Amazon and Univ of Calgary to present their latest progress in both indoor and outdoor mapping and were well received by the computer vision community.

In 2022, we would like to continue the momentum and organize a full day tutorial, to include both outdoor mapping and indoor mapping, to make the tutorial more valuable for the computer vision community. This tutorial session brings together people from around the world who are practicing computer vision research for mapping/location-based reasoning in both industry and academia, and would cover the following topics of interests (including but not limited to):