Mapillary Joins Berkeley DeepDrive

We’re incredibly excited to join University of California Berkeley’s DeepDrive initiative to help push computer vision and deep learning forward. This, we hope, will improve understanding of street images for safer cities, autonomous cars, and better maps.

Initially the research collaboration will focus on semantic segmentation and structure from motion, two of the core technologies that power Mapillary. UC Berkeley is a world leader in these fields and also leads development of the caffe deep learning library that powers a lot of deep learning today.

Semantic segmentation
Our semantic segmentation

Point clouds
Our point clouds, generated from community photos

Mapillary will collaborate and share research, and also contribute with data for the DeepDrive project. We’re looking forward to collaborating with an amazing group of researchers and industrial partners.

/Jan Erik

Continue the conversation