no code implementations • 31 Oct 2022 • Iain Haughton, Edgar Sucar, Andre Mouton, Edward Johns, Andrew J. Davison
Neural fields can be trained from scratch to represent the shape and appearance of 3D scenes efficiently.
no code implementations • 6 Oct 2022 • Kirill Mazur, Edgar Sucar, Andrew J. Davison
General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped.
1 code implementation • 5 Apr 2022 • Joseph Ortiz, Alexander Clegg, Jing Dong, Edgar Sucar, David Novotny, Michael Zollhoefer, Mustafa Mukadam
We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction.
no code implementations • 29 Nov 2021 • Shuaifeng Zhi, Edgar Sucar, Andre Mouton, Iain Haughton, Tristan Laidlow, Andrew J. Davison
ILabel's underlying model is a multilayer perceptron (MLP) trained from scratch in real-time to learn a joint neural scene representation.
no code implementations • 13 Sep 2021 • Joseph Ortiz, Talfan Evans, Edgar Sucar, Andrew J. Davison
Scene graphs represent the key components of a scene in a compact and semantically rich way, but are difficult to build during incremental SLAM operation because of the challenges of robustly identifying abstract scene elements and optimising continually changing, complex graphs.
3 code implementations • ICCV 2021 • Edgar Sucar, Shikun Liu, Joseph Ortiz, Andrew J. Davison
We show for the first time that a multilayer perceptron (MLP) can serve as the only scene representation in a real-time SLAM system for a handheld RGB-D camera.
1 code implementation • CVPR 2020 • Kentaro Wada, Edgar Sucar, Stephen James, Daniel Lenton, Andrew J. Davison
Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion.
no code implementations • 9 Apr 2020 • Edgar Sucar, Kentaro Wada, Andrew Davison
The choice of scene representation is crucial in both the shape inference algorithms it requires and the smart applications it enables.
no code implementations • 7 Nov 2017 • Edgar Sucar, Jean-Bernard Hayet
This work proposes a new, online algorithm for estimating the local scale correction to apply to the output of a monocular SLAM system and obtain an as faithful as possible metric reconstruction of the 3D map and of the camera trajectory.
Robotics
no code implementations • 27 May 2017 • Edgar Sucar, Jean-Bernard Hayet
This paper proposes a novel method to estimate the global scale of a 3D reconstructed model within a Kalman filtering-based monocular SLAM algorithm.