Sotabase

Career

· Chief Scientist, Niantic Spatial, Inc.2025–
· Professor Of Artificial Intelligence, University of Oxford2025–
· Chief Scientist, Niantic, Inc.2020–2025
· CSO, 6D.ai2017–2020
· Associate Professor, University of Oxford2015–2025
· Postdoctoral Research Assistant, University of Oxford2012–2012
· Postdoctoral Research Fellow, University of Oxford2012–2015
· Consultant, Oxford University Innovation2009–
· Doctor of Philosophy (PhD), Computer Vision, University of Oxford2008–2012
· Bachelor of Science (BS), Computer Engineering, Universitatea Tehnică Gheorghe Asachi din Iaşi2003–2008

Publications (96)

GA-Net: Guided Aggregation Net for End-To-End Stereo Matching
Computer Vision and Pattern Recognition · 2019
763
cited
NeRF-: Neural Radiance Fields Without Known Camera Parameters
arXiv.org · 2021
676
cited
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
Computer Vision and Pattern Recognition · 2021
340
cited
NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
Computer Vision and Pattern Recognition · 2022
320
cited
Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices
IEEE Transactions on Visualization and Computer Graphics · 2015
319
cited
PWP3D: Real-Time Segmentation and Tracking of 3D Objects
International Journal of Computer Vision · 2012
234
cited
fastHOG – a real-time GPU implementation of HOG
2011
219
cited
Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction
IEEE International Conference on Robotics and Automation · 2015
214
cited
RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets
European Conference on Computer Vision · 2018
209
cited
Domain-invariant Stereo Matching Networks
European Conference on Computer Vision · 2019
201
cited
Dual-Resolution Correspondence Networks
Neural Information Processing Systems · 2020
189
cited
NeRF--: Neural Radiance Fields Without Known Camera Parameters
2021
188
cited
Dense Reconstruction Using 3D Object Shape Priors
2013 IEEE Conference on Computer Vision and Pattern Recognition · 2013
164
cited
Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure
European Conference on Computer Vision · 2016
129
cited
Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2018
127
cited
SimpleRecon: 3D Reconstruction Without 3D Convolutions
European Conference on Computer Vision · 2022
124
cited
InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure
arXiv.org · 2017
115
cited
Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation
IEEE International Conference on Computer Vision · 2021
110
cited
FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2019
103
cited
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses
Computer Vision and Pattern Recognition · 2023
101
cited
Sotabase