Papers
2
Total Citations
47
H-Index
2
About
Daqi Liu is a computer vision and robotics researcher specializing in event-based perception and visual odometry. His work centers on harnessing the unique properties of event cameras — sensors renowned for their low latency, high dynamic range, and high temporal resolution — to advance robotic navigation and scene understanding. Liu's most notable contribution, "Spatiotemporal Registration for Event-based Visual Odometry" (2021), has garnered 37 citations and addresses a fundamental challenge in the field: the computational cost of contrast maximisation methods used to recover motion from event data. By rethinking how events are spatiotemporally registered, Liu offered a more scalable and efficient framework for motion estimation, pushing the boundaries of what event-based systems can achieve in real-world settings. Building on this foundation, his 2022 paper on asynchronous optimisation for event-based visual odometry further explores how to fully exploit the asynchronous, data-driven nature of event cameras — a critical step toward truly low-latency robotic perception systems. Together, these contributions position Liu as an emerging voice in neuromorphic vision and autonomous systems research, making his work particularly relevant for students and researchers working at the intersection of computer vision, robotics, and unconventional sensing technologies.
Research Focus
Key Achievements
Top Papers
- 1Spatiotemporal Registration for Event-based Visual Odometry37 citations · 2021
- 2Asynchronous Optimisation for Event-based Visual Odometry10 citations · 2022
Key Collaborators
Related papers
Researchers in this area
Labs working in this area
If you're exploring the applied side
Commercial systems in adjacent areas you may find useful as a starting point. This is not a claim that the research here is used in them — academia and industry often move on separate tracks.
- Related commercial systems
Alphasense PositionSevensense
Suggested by topic similarity — not advertising or endorsement.