DoC researchers receive Best Demo Award for Gaussian Splatting SLAM project
The CVPR 2024 conference, saw over 12,000 participants from 76 countries.
The 2024 Computer Vision and Pattern Recognition (CVPR) Conference, held in Seattle, WA, USA, witnessed record-breaking participation and groundbreaking innovations. Amidst the bustling event, a team from Imperial distinguished itself by winning the Best Demo Award for their project "Gaussian Splatting SLAM".
The awarded demo was a collaborative effort by Hidenobu Matsuki and Professor Andrew J. Davison from the Dyson Robotics Laboratory, and Riku Murai and Prof Paul Kelly from the Software Performance Optimisation Group at Imperial. Their project, Gaussian Splatting SLAM, showcased a novel approach to simultaneous localization and mapping (SLAM) using Gaussian splatting techniques, which impressed both attendees and judges alike.
"Winning the Best Demo Award at CVPR 2024 is a testament to the innovative spirit and technical excellence of our team at Imperial," said Professor Andrew J. Davison. "We are thrilled to receive this recognition and look forward to further advancing our research in this exciting field."
The CVPR 2024 conference, which saw over 12,000 participants from 76 countries, is renowned as the leading event in computer vision and pattern recognition. This year's conference featured a record number of paper submissions, with only 23.6% of the 11,532 submissions accepted for presentation.The competitive nature of the event underscores the significance of the Best Demo Award.
In addition to the award-winning Gaussian Splatting SLAM, the conference also recognized other notable demos, including an honorable mention for "SuperPrimitive: Scene Reconstruction at a Primitive Level" by Kirill Mazur, Gwangbin Bae, and Andrew J. Davison, also from the Dyson Robotics Lab at Imperial.
Imperial's strong showing at CVPR 2024 highlights the institution's leading role in advancing computer vision technology. The Department of Computing, through its cutting-edge research and collaborative efforts, continues to push the boundaries of what is possible in the field.
About CVPR 2024
The Computer Vision and Pattern Recognition Conference (CVPR) is the foremost annual event for computer vision research, bringing together experts from academia, industry, and government. Sponsored by the IEEE Computer Society and the Computer Vision Foundation, CVPR 2024 was held in June at the Seattle Convention Center in Seattle, WA, USA, and virtually. For more information, visit CVPR 2024.
Article text (excluding photos or graphics) © Imperial College London.
Photos and graphics subject to third party copyright used with permission or © Imperial College London.