News and Publications

Implicit Depth: Niantic's work on estimating occlusions for AR has been accepted to CVPR 2023!

April 2023

SimpleRecon: Niantic's work on estimating depth from video has been accepted at ECCV 2022!

August 2022

Niantic's work on making objects disappear in novel views has been accepted to CVPR 2023!

March 2023

Niantic's work on estimating visible and hidden traversable space from an RGB image has been accepted for CVPR 2020

June 2020

Niantic's work on depth estimation from monocular images has been accepted for publication at ICCV 2019

August 2019

Visual Camera Re-Localization using Graph Neural Networks and Relative Pose Supervision

3DV 2021

Featured Publications

Virtual Occlusions Through Implicit Depth
CVPR 2023
Jamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel J Brostow, Sara Vicente, Oisin Mac Aodha, Michael Firman
Removing Objects From Neural Radiance Fields
CVPR 2023
Silvan Weder, Guillermo Garcia-Hernando, Aron Monszpart, Marc Pollefeys, Gabriel Brostow, Michael Firman, Sara Vicente
Two-view Geometry Scoring Without Correspondences
CVPR 2023
Axel Barroso-Laguna, Eric Brachmann, Victor Adrian Prisacariu, Gabriel Brostow, Daniyar Turmukhambetov
DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models
CVPR 2023
Jamie Wynn, Daniyar Turmukhambetov
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses
CVPR 2023
Eric Brachmann, Tommaso Cavallari, Victor Adrian Prisacariu
Heightfields for Efficient Scene Reconstruction for AR
WACV 2023
Jamie Watson, Sara Vicente, Oisin Mac Aodha, Clément Godard, Gabriel Brostow, Michael Firman
SimpleRecon: 3D Reconstruction Without 3D Convolutions
ECCV 2022
Mohamed Sayed, John Gibson, Jamie Watson, Victor Adrian Prisacariu, Michael Firman, Clément Godard
Camera Pose Estimation and Localization with Active Audio Sensing
ECCV 2022
Karren Yang, Michael Firman, Eric Brachmann, Clément Godard
Map-free Visual Relocalization: Metric Pose Relative to a Single Image
ECCV 2022
Eduardo Arnold, Jamie Wynn, Sara Vicente, Guillermo Garcia-Hernando, Áron Monszpart, Victor Adrian Prisacariu, Daniyar Turmukhambetov, Eric Brachmann
Learning Structured Gaussians to Approximate Deep Ensembles
CVPR 2022
Ivor J. A. Simpson, Sara Vicente, Neill D. F. Campbell
Visual Camera Re-Localization using Graph Neural Networks and Relative Pose Supervision
3DV 2021
Mehmet Ozgur Turkoglu, Eric Brachmann, Konrad Schindler, Gabriel Brostow, Aron Monszpart
On the Limits of Pseudo Ground Truth in Visual Camera Re-Localisation
ICCV 2021
Eric Brachmann, Martin Humenberger, Carsten Rother, Torsten Sattler
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images
CVPR 2021
Florian Kluger, Hanno Ackermann, Eric Brachmann, Michael Ying Yang, Bodo Rosenhahn
Single Image Depth Prediction with Wavelet Decomposition
CVPR 2021
Michael Ramamonjisoa, Michael Firman, Jamie Watson, Vincent Lepetit, Daniyar Turmukhambetov
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
CVPR 2021
Jamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel Brostow, Michael Firman
Panoptic Segmentation Forecasting
CVPR 2021
Colin Graber, Grace Tsai, Michael Firman, Gabriel Brostow, Alexander Schwing
Learning to Predict Repeatability of Interest Points
ICRA 2021
Anh-Dzung Doan, Daniyar Turmukhambetov, Yasir Latif, Tat-Jun Chin, Soohyun Bae
Learning Stereo from Single Images
ECCV 2020
Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov, Gabriel J. Brostow, Michael Firman
Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
NeurIPS 2020
Sebastien Ehrhardt, Oliver Groth, Aron Monszpart, Martin Engelcke, Ingmar Posner, Niloy Mitra, Andrea Vedaldi
Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings
ECCV 2020
Anita Rau, Guillermo Garcia-Hernando, Danail Stoyanov, Gabriel J. Brostow and Daniyar Turmukhambetov
Single-Image Depth Prediction Makes Feature Matching Easier
ECCV 2020
Carl Toft, Daniyar Turmukhambetov, Torsten Sattler, Fredrik Kahl and Gabriel J. Brostow
Footprints and Free Space from a Single Color Image
CVPR 2020
Jamie Watson, Michael Firman, Aron Monszpart, Gabriel J. Brostow
Self-Supervised Monocular Depth Hints
ICCV 2019
Jamie Watson, Michael Firman, Gabriel J. Brostow, Daniyar Turmukhambetov
Digging Into Self-Supervised Monocular Depth Estimation
ICCV 2019
Clément Godard, Oisin Mac Aodha, Michael Firman, Gabriel Brostow
An Efficient 3D CNN for Action/Object Segmentation in Video
BMVC 2019
Rui Hou, Chen Chen, Rahul Sukthankar, Mubarak Shah
iMapper: Interaction-guided Scene Mapping from Monocular Videos
SIGGRAPH 2019
Aron Monszpart, Paul Guerrero, Duygu Ceylan, Ersin Yumer, Niloy J. Mitra
Unsupervised Intuitive Physics from Visual Observations
ACCV 2018
Sébastien Ehrhardt, Aron Monszpart, Niloy J. Mitra, Andrea Vedaldi
Unsupervised Monocular Depth Estimation with Left-Right Consistency
CVPR 2017
Clément Godard, Oisin Mac Aodha, Gabriel J. Brostow