Michael Firman

38 papers A* 12A 3Journal 16Unranked 7
YearRankTypeTitle / Venue / Authors
2025 J jnl
Complete Gaussian Splats from a Single Image with Denoising Diffusion Models.
CoRR
Ziwei Liao, Mohamed Sayed, Steven L. Waslander, Sara Vicente, Daniyar Turmukhambetov, Michael Firman
2025 A* conf
MVSAnywhere: Zero-Shot Multi-View Stereo.
CVPR
Sergio Izquierdo, Mohamed Sayed, Michael Firman, Guillermo Garcia-Hernando, Daniyar Turmukhambetov, Javier Civera, Oisin Mac Aodha, Gabriel J. Brostow, Jamie Watson
2025 J jnl
MVSAnywhere: Zero-Shot Multi-View Stereo.
CoRR
Sergio Izquierdo, Mohamed Sayed, Michael Firman, Guillermo Garcia-Hernando, Daniyar Turmukhambetov, Javier Civera, Oisin Mac Aodha, Gabriel J. Brostow, Jamie Watson
2024 A* conf
AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings.
CVPR
Jamie Watson, Filippo Aleotti, Mohamed Sayed, Zawar Qureshi, Oisin Mac Aodha, Gabriel J. Brostow, Michael Firman, Sara Vicente
2024 J jnl
AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings.
CoRR
Jamie Watson, Filippo Aleotti, Mohamed Sayed, Zawar Qureshi, Oisin Mac Aodha, Gabriel J. Brostow, Michael Firman, Sara Vicente
2024 — conf
DoubleTake: Geometry Guided Depth Estimation.
ECCV (73)
Mohamed Sayed, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel J. Brostow, Sara Vicente, Michael Firman
2024 J jnl
DoubleTake: Geometry Guided Depth Estimation.
CoRR
Mohamed Sayed, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel J. Brostow, Sara Vicente, Michael Firman
2023 A conf
Heightfields for Efficient Scene Reconstruction for AR.
WACV
Jamie Watson, Sara Vicente, Oisin Mac Aodha, Clément Godard, Gabriel J. Brostow, Michael Firman
2023 A* conf
Removing Objects From Neural Radiance Fields.
CVPR
Silvan Weder, Guillermo Garcia-Hernando, Áron Monszpart, Marc Pollefeys, Gabriel J. Brostow, Michael Firman, Sara Vicente
2023 A* conf
Virtual Occlusions Through Implicit Depth.
CVPR
Jamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel J. Brostow, Sara Vicente, Oisin Mac Aodha, Michael Firman
2023 J jnl
Virtual Occlusions Through Implicit Depth.
CoRR
Jamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel J. Brostow, Sara Vicente, Oisin Mac Aodha, Michael Firman
2022 — conf
Camera Pose Estimation and Localization with Active Audio Sensing.
ECCV (37)
Karren Yang, Michael Firman, Eric Brachmann, Clément Godard
2022 J jnl
Removing Objects From Neural Radiance Fields.
CoRR
Silvan Weder, Guillermo Garcia-Hernando, Áron Monszpart, Marc Pollefeys, Gabriel J. Brostow, Michael Firman, Sara Vicente
2022 — conf
SimpleRecon: 3D Reconstruction Without 3D Convolutions.
ECCV (33)
Mohamed Sayed, John Gibson, Jamie Watson, Victor Prisacariu, Michael Firman, Clément Godard
2022 J jnl
SimpleRecon: 3D Reconstruction Without 3D Convolutions.
CoRR
Mohamed Sayed, John Gibson, Jamie Watson, Victor Prisacariu, Michael Firman, Clément Godard
2021 A* conf
Panoptic Segmentation Forecasting.
CVPR
Colin Graber, Grace Tsai, Michael Firman, Gabriel J. Brostow, Alexander G. Schwing
2021 — conf
Panoptic Segmentation Forecasting.
CVPR Workshops
Colin Graber, Grace Tsai, Michael Firman, Gabriel J. Brostow, Alexander G. Schwing
2021 J jnl
Panoptic Segmentation Forecasting.
CoRR
Colin Graber, Grace Tsai, Michael Firman, Gabriel J. Brostow, Alexander G. Schwing
2021 J jnl
Single Image Depth Estimation using Wavelet Decomposition.
CoRR
Michaël Ramamonjisoa, Michael Firman, Jamie Watson, Vincent Lepetit, Daniyar Turmukhambetov
2021 A* conf
Single Image Depth Prediction With Wavelet Decomposition.
CVPR
Michaël Ramamonjisoa, Michael Firman, Jamie Watson, Vincent Lepetit, Daniyar Turmukhambetov
2021 A* conf
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth.
CVPR
Jamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel J. Brostow, Michael Firman
2021 J jnl
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth.
CoRR
Jamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel J. Brostow, Michael Firman
2020 J jnl
DiverseNet: When One Right Answer is not Enough.
CoRR
Michael Firman, Neill D. F. Campbell, Lourdes Agapito, Gabriel J. Brostow
2020 A* conf
Footprints and Free Space From a Single Color Image.
CVPR
Jamie Watson, Michael Firman, Áron Monszpart, Gabriel J. Brostow
2020 J jnl
Footprints and Free Space from a Single Color Image.
CoRR
Jamie Watson, Michael Firman, Áron Monszpart, Gabriel J. Brostow
2020 — conf
Learning Stereo from Single Images.
ECCV (1)
Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov, Gabriel J. Brostow, Michael Firman
2020 J jnl
Learning Stereo from Single Images.
CoRR
Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov, Gabriel J. Brostow, Michael Firman
2019 A* conf
Digging Into Self-Supervised Monocular Depth Estimation.
ICCV
Clément Godard, Oisin Mac Aodha, Michael Firman, Gabriel J. Brostow
2019 A* conf
Self-Supervised Monocular Depth Hints.
ICCV
Jamie Watson, Michael Firman, Gabriel J. Brostow, Daniyar Turmukhambetov
2019 J jnl
Self-Supervised Monocular Depth Hints.
CoRR
Jamie Watson, Michael Firman, Gabriel J. Brostow, Daniyar Turmukhambetov
2018 J jnl
Bat detective - Deep learning tools for bat acoustic signal detection.
PLoS Comput. Biol.
Oisin Mac Aodha, Rory Gibb, Kate E. Barlow, Ella Browning, Michael Firman, Robin Freeman, Briana Harder, Libby Kinsey, Gary R. Mead, Stuart E. Newson, Ivan Pandourski, Stuart Parsons, Jon Russ, Abigel Szodoray-Paradi, Farkas Szodoray-Paradi, Elena Tilova, Mark A. Girolami, Gabriel J. Brostow, Kate E. Jones
2018 A* conf
DiverseNet: When One Right Answer Is Not Enough.
CVPR
Michael Firman, Neill D. F. Campbell, Lourdes Agapito, Gabriel J. Brostow
2018 — conf
RecurBot: Learn to Auto-complete GUI Tasks From Human Demonstrations.
CHI Extended Abstracts
Thanapong Intharah, Michael Firman, Gabriel J. Brostow
2016 — conf
RGBD Datasets: Past, Present and Future.
CVPR Workshops
Michael Firman
2016 J jnl
RGBD Datasets: Past, Present and Future.
CoRR
Michael Firman
2016 A* conf
Structured Prediction of Unobserved Voxels from a Single Depth Image.
CVPR
Michael Firman, Oisin Mac Aodha, Simon J. Julier, Gabriel J. Brostow
2013 A conf
Learning to discover objects in RGB-D images using correlation clustering.
IROS
Michael Firman, Diego Thomas, Simon Julier, Akihiro Sugimoto
2011 A conf
'Misspelled' visual words in unsupervised range data classification: the effect of noise on classification performance.
IROS
Michael Firman, Simon Julier