Inventing the Intelligent Spaces of Tomorrow
We are a global, multidisciplinary team advancing machine learning, AI, computer vision, and graphics to enable new ways of exploring, understanding, and interacting in a shared augmented world. We collaborate with leading universities worldwide, publish at top conferences, and share our code and insights with the scientific community.
-
CoCreatAR: Enhancing Authoring of Outdoor Augmented Reality Experiences Through Asymmetric CollaborationNels Numan, Gabriel Brostow, Suhyun Park, Simon Julier, Anthony Steed, Jessica Van BrummelenCHI 2025
-
HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global PositioningEugene Valassakis, Guillermo Garcia-HernandoECCV 2024
-
DoubleTake: Geometry Guided Depth EstimationMohamed Sayed, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel Brostow, Sara Vicente, Michael FirmanECCV 2024
-
Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a RelocalizerEric Brachmann, Jamie Wynn, Shuai Chen, Tommaso Cavallari, Áron Monszpart, Daniyar Turmukhambetov, Victor Adrian PrisacariuECCV 2024
-
Don't Look Now: Audio/Haptic Guidance for 3D Scanning of LandmarksJessica Van Brummelen, Liv Piper Urwin, Oliver James Johnston, Mohamed Sayed, Gabriel BrostowCHI 2024
-
AirPlanes: Accurate Plane Estimation via 3D-Consistent EmbeddingsJamie Watson, Filippo Aleotti, Mohamed Sayed, Zawar Qureshi, Oisin Mac Aodha, Gabriel Brostow, Michael Firman, and Sara VicenteCVPR 2024
-
Matching 2D Images in 3D: Metric Relative Pose from Metric CorrespondencesAxel Barroso-Laguna, Sowmya Munukutla, Victor Adrian Prisacariu, Eric BrachmannCVPR 2024
-
Virtual Occlusions Through Implicit DepthJamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel J Brostow, Sara Vicente, Oisin Mac Aodha, Michael FirmanCVPR 2023
-
Removing Objects From Neural Radiance FieldsSilvan Weder, Guillermo Garcia-Hernando, Aron Monszpart, Marc Pollefeys, Gabriel Brostow, Michael Firman, Sara VicenteCVPR 2023
-
Two-view Geometry Scoring Without CorrespondencesAxel Barroso-Laguna, Eric Brachmann, Victor Adrian Prisacariu, Gabriel Brostow, Daniyar TurmukhambetovCVPR 2023
-
DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion ModelsJamie Wynn, Daniyar TurmukhambetovCVPR 2023
-
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and PosesEric Brachmann, Tommaso Cavallari, Victor Adrian PrisacariuCVPR 2023
-
Heightfields for Efficient Scene Reconstruction for ARJamie Watson, Sara Vicente, Oisin Mac Aodha, Clément Godard, Gabriel Brostow, Michael FirmanWACV 2023
-
SimpleRecon: 3D Reconstruction Without 3D ConvolutionsMohamed Sayed, John Gibson, Jamie Watson, Victor Adrian Prisacariu, Michael Firman, Clément GodardECCV 2022
-
Camera Pose Estimation and Localization with Active Audio SensingKarren Yang, Michael Firman, Eric Brachmann, Clément GodardECCV 2022
-
Map-free Visual Relocalization: Metric Pose Relative to a Single ImageEduardo Arnold, Jamie Wynn, Sara Vicente, Guillermo Garcia-Hernando, Áron Monszpart, Victor Adrian Prisacariu, Daniyar Turmukhambetov, Eric BrachmannECCV 2022
-
Learning Structured Gaussians to Approximate Deep EnsemblesIvor J. A. Simpson, Sara Vicente, Neill D. F. CampbellCVPR 2022
-
Visual Camera Re-Localization using Graph Neural Networks and Relative Pose SupervisionMehmet Ozgur Turkoglu, Eric Brachmann, Konrad Schindler, Gabriel Brostow, Aron Monszpart3DV 2021
-
On the Limits of Pseudo Ground Truth in Visual Camera Re-LocalisationEric Brachmann, Martin Humenberger, Carsten Rother, Torsten SattlerICCV 2021
-
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB ImagesFlorian Kluger, Hanno Ackermann, Eric Brachmann, Michael Ying Yang, Bodo RosenhahnCVPR 2021
-
Single Image Depth Prediction with Wavelet DecompositionMichael Ramamonjisoa, Michael Firman, Jamie Watson, Vincent Lepetit, Daniyar TurmukhambetovCVPR 2021
-
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular DepthJamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel Brostow, Michael FirmanCVPR 2021
-
Panoptic Segmentation ForecastingColin Graber, Grace Tsai, Michael Firman, Gabriel Brostow, Alexander SchwingCVPR 2021
-
Learning to Predict Repeatability of Interest PointsAnh-Dzung Doan, Daniyar Turmukhambetov, Yasir Latif, Tat-Jun Chin, Soohyun BaeICRA 2021
-
Learning Stereo from Single ImagesJamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov, Gabriel J. Brostow, Michael FirmanECCV 2020
-
Physically Plausible Multi-Object Scene Synthesis Using Structured Latent SpacesSebastien Ehrhardt, Oliver Groth, Aron Monszpart, Martin Engelcke, Ingmar Posner, Niloy Mitra, Andrea VedaldiNeurIPS 2020
-
Predicting Visual Overlap of Images Through Interpretable Non-Metric Box EmbeddingsAnita Rau, Guillermo Garcia-Hernando, Danail Stoyanov, Gabriel J. Brostow and Daniyar TurmukhambetovECCV 2020
-
Single-Image Depth Prediction Makes Feature Matching EasierCarl Toft, Daniyar Turmukhambetov, Torsten Sattler, Fredrik Kahl and Gabriel J. BrostowECCV 2020
-
Footprints and Free Space from a Single Color ImageJamie Watson, Michael Firman, Aron Monszpart, Gabriel J. BrostowCVPR 2020
-
Self-Supervised Monocular Depth HintsJamie Watson, Michael Firman, Gabriel J. Brostow, Daniyar TurmukhambetovICCV 2019
-
Digging Into Self-Supervised Monocular Depth EstimationClément Godard, Oisin Mac Aodha, Michael Firman, Gabriel BrostowICCV 2019
-
An Efficient 3D CNN for Action/Object Segmentation in VideoRui Hou, Chen Chen, Rahul Sukthankar, Mubarak ShahBMVC 2019
-
iMapper: Interaction-guided Scene Mapping from Monocular VideosAron Monszpart, Paul Guerrero, Duygu Ceylan, Ersin Yumer, Niloy J. MitraSIGGRAPH 2019
-
Unsupervised Intuitive Physics from Visual ObservationsSébastien Ehrhardt, Aron Monszpart, Niloy J. Mitra, Andrea VedaldiACCV 2018
-
Unsupervised Monocular Depth Estimation with Left-Right ConsistencyClément Godard, Oisin Mac Aodha, Gabriel J. BrostowCVPR 2017