Edgar Sucar

I am Postdocotral Fellow in the VGG at the Univiersity of Oxford working with Prof. Andrea Vedaldi. Previously, I completed a PhD in the Dyson Robotics Lab at Imperial College London under the supervision of Prof. Andrew Davison.

I am generally interested in developing methods for 3D/4D scene understanding that enable robots to have meaningful interactions with their environment. I enjoy building practical real-time systems.

Email / Scholar / Twitter

Research

Research Interests: Computer Vision, SLAM, 4D Reconstruction, Robotics.

	V-DPM: Video Reconstruction with Dynamic Point Maps Edgar Sucar, Eldar Insafutdinov, Zihang Lai, Andrea Vedaldi coming soon.. project page / paper
	Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction Edgar Sucar, Zihang Lai, Eldar Insafutdinov, Andrea Vedaldi ICCV, 2025 (Highlight) project page / paper
	Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding Kirill Mazur, Edgar Sucar, Andrew J. Davison ICRA, 2023 project page / paper
	iMODE: Real-Time Incremental Monocular Dense Mapping Using Neural Field Hidenobu Matsuki, Edgar Sucar, Tristan Laidlow, Kentaro Wada, Raluca Scona, Andrew J. Davison ICRA, 2023 (Oral Presentation, Best Navigation Paper Award Finalist) paper
	Real-time Mapping of Physical Scene Properties with an Autonomous Robot Experimenter Iain Haughton, Edgar Sucar, Andre Mouton, Edward Johns, Andrew J. Davison CoRL, 2022 (Oral Presentation) project page / paper
	iSDF: Real-Time Neural Signed Distance Fields for Robot Perception Joseph Ortiz, Alexander Clegg, Jing Dong, Edgar Sucar, David Novotny, Michael Zollhoefer, Mustafa Mukadam RSS, 2022 project page / paper
	Incremental Abstraction in Distributed Probabilistic SLAM Graphs Joseph Ortiz, Talfan Evans, Edgar Sucar, Andrew J. Davison ICRA, 2022 project page / paper
	iLabel: Interactive Neural Scene Labelling Shuaifeng Zhi, Edgar Sucar, Andre Mouton, Iain Haughton, Tristan Laidlow, Andrew J. Davison RA-L, 2022 project page / paper
	iMAP: Implicit Mapping and Positioning in Real-Time Edgar Sucar, Shikun Liu, Joseph Ortiz, Andrew J. Davison ICCV, 2021 project page / paper
	NodeSLAM: Neural object descriptors for multi-view shape reconstruction Edgar Sucar, Kentaro Wada, Andrew Davison 3DV, 2020 project page / paper
	Morefusion: Multi-object reasoning for 6d pose estimation from volumetric fusion Kentaro Wada, Edgar Sucar, Stephen James, Daniel Lenton, Andrew J. Davison CVPR, 2020 project page / paper
	Bayesian scale estimation for monocular SLAM based on generic object detection for correcting scale drift Edgar Sucar, Jean-Bernard Hayet ICRA, 2018 paper

Website template: source code.