Papers
11
Total Citations
839
H-Index
8
About
Richard Newcombe is a leading researcher in 3D computer vision and robotics, whose work has fundamentally shaped how machines perceive and interact with the physical world. He is best known for pioneering DeepSDF, a groundbreaking method for learning continuous signed distance functions that revolutionized 3D shape representation, enabling high-fidelity rendering and reconstruction with remarkable compression. This work alone has garnered over 250 citations. Newcombe has also made seminal contributions to real-time tracking and dense visual SLAM, developing the DART framework for articulated object tracking and advancing self-supervised visual descriptor learning for dense correspondence. His recent work on OrienterNet bridges the gap between 2D maps and 3D localization, offering a practical alternative to expensive point cloud-based systems. With over 800 total citations across his most influential papers, Newcombe’s research consistently pushes the boundaries of what is possible in augmented reality, robotics, and 3D scene understanding, making him a pivotal figure in the field.
Research Focus
Key Achievements
Top Papers
- 1DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation259 citations · 2019
- 2Self-Supervised Visual Descriptor Learning for Dense Correspondence170 citations · 2016
- 3DART: Dense Articulated Real-Time Tracking136 citations · 2014
- 4OrienterNet: Visual Localization in 2D Public Maps with Neural Matching78 citations · 2023
- 5Depth-based tracking with physical constraints for robot manipulation69 citations · 2015
- 6DART: dense articulated real-time tracking with consumer depth cameras57 citations · 2015
- 7ODAM: Object Detection, Association, and Mapping using Posed RGB Video29 citations · 2021
- 8Dense Visual SLAM22 citations · 2012
- 9Controlling an Anthropomimetic Robot: A Preliminary Investigation8 citations · 2007
- 10