Resources Hub
Discover the latest events, news, products, and research from the Niantic Spatial Platform Team.
Knowledge and Support
Latest Blog Posts
View AllNiantic Spatial's 3D Reconstruction Technology Assessed "Awardable" on the Tradewinds Solutions Marketplace
Niantic Spatial, a leading commercial dual-use provider of geospatial AI technology, announced that it has achieved "Awardable" status through the Chief Digital and Artificial Intelligence Office's (CDAO) Tradewinds Solutions Marketplace for its 3D Reconstruction platform.
Ground Truth: How We Create Geometrically Accurate Reconstructions
Many AI-generated world models are built to produce something that looks right. Niantic Spatial's reconstruction pipeline is built to produce something that is right, with geometrically accurate models that reflect the physical reality of the space that was captured. This is a critical step required for creating real-world foundation models for physical AI.
The distinction matters to anyone operating in the real world. Infrastructure teams can use geometrically accurate reconstructions to inspect assets remotely without site visits. Insurance and energy companies use them in site analysis and asset management. Robotics teams can use them as real-to-sim training data. This post explains how the pipeline works and what makes that level of accuracy hard to achieve at scale.
Publications
Virtual Occlusions Through Implicit Depth
CVPR 2023
Jamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel Brostow, Sara Vicente, Oisin Mac Aodha, Michael Firman
SimpleRecon: 3D Reconstruction without 3D Convolutions
ECCV 2022
Mohamed Sayed, John Gibson, Jamie Watson, Victor Adrian Prisacariu, Michael Firman, Clément Godard
Removing Objects From Neural Radiance Fields
CVPR 2023
Silvan Weder, Guillermo Garcia-Hernando, Áron Monszpart, Marc Pollefeys, Gabriel Brostow, Michael Firman, Sara Vicente1
Footprints and Free Space from a Single Color Image
CVPR 2020
Jamie Watson, Michael Firman, Aron Monszpart, Gabriel J. Brostow
Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs
ICCV 2019
Jamie Watson, Michael Firman, Gabriel J. Brostow and Daniyar Turmukhambetov
Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision
3DV 2021
Mehmet Özgür Türkoǧlu, Eric Brachmann, Konrad Schindler, Gabriel J. Brostow, Áron Monszpart