Saying the winners of the Metropolis-Scale 3D Map Making with Mapillary Metropolis request for proposals

In July 2021, Meta started the benchmarking City-Scale 3D Map Making with Mapillary Metropolis Request for Proposals (RFP). Today we announce the winners of this award.

View tender

Earlier this year we introduced a novel city-level data set called Mapillary Metropolis, which was developed with the aim of creating a completely new and complex benchmarking paradigm for training and testing computer vision algorithms in the context of semantic 3D mapping.

For this call, we looked for research proposals that used Mapillary Metropolis to improve basic computer vision algorithms that use one or preferably more data modalities from our dataset to improve the 3D semantic building. We were particularly interested in the following areas:

  • City-scale 3D modeling from heterogeneous data sources
  • ML for object recognition, tracking and dense labeling
  • Image-based comparison, relocalization and retrieval

The RFP attracted 29 proposals from 27 universities and institutions around the world. Thank you to everyone who took the time to submit a proposal and congratulations to the winners.

Research Award Winner

Unless otherwise noted, lead investigators are listed first.

Factored, object-centered implicit representations for city-scale scenes
Jiajun Wu, Hong-Xing (Koven) Yu (Stanford University)

Multimodal visual 6DOF relocation in Mapillary Metropolis
Torsten Sattler, Zuzana Kukelova (Czech Technical University Prague)

Neural feature fields for photorealistic scene synthesis
Andreas Geiger (University of Tübingen, Germany)

Comments are closed.