Presentation

<
RTG-SLAM: Real-time 3D Reconstruction at Scale Using Gaussian Splatting
SessionFast Radiance Fields
DescriptionRTG-SLAM is a real-time 3D reconstruction system using Gaussian splatting. It is also memory efficient, enabling reconstruction of large-scale environments. Comparisons demonstrate RTG-SLAM runs at around twice the speed of the state-of-the-art, NeRF-based SLAM, with around half the memory cost (e.g., 17.9 fps, 8.8 GB versus 8.65 fps, 17.3 GB).
Authors
Zhexi Peng
Zhejiang University
Tianjia Shao
Zhejiang University
Yong Liu
Zhejiang University
Jingke Zhou
Zhejiang University
Yin Yang
University of Utah
Jingdong Wang
Baidu Research
Kun Zhou
Zhejiang University
Event Type
Technical Paper
TimeMonday, 29 July 20249:00am - 9:10am MDT
LocationMile High 1
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 20249:00am - 10:30am MDTMile High 1
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Geometry
Modeling
Rendering
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday
Next PresentationNext PresentationBoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes