首页|New Robotics and Automation Study Results from Sun Yat-sen University Described (H3-mapping: Quasi-heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation)
New Robotics and Automation Study Results from Sun Yat-sen University Described (H3-mapping: Quasi-heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Robotics - Ro botics and Automation have been published. According to news originating from Zh uhai, People’s Republic of China, by NewsRx correspondents, research stated, “In recent years, implicit online dense mapping methods have achieved high-quality reconstruction results, showcasing great potential in robotics, AR/VR, and digit al twins applications. However, existing methods struggle with slow texture mode ling which limits their real-time performance.” Our news journalists obtained a quote from the research from Sun Yat-sen Univers ity, “To address these limitations, we propose a NeRF-based dense mapping method that enables faster and higher-quality reconstruction. To improve texture model ing, we introduce quasi-heterogeneous feature grids, which inherit the fast quer ying ability of uniform feature grids while adapting to varying levels of textur e complexity. Additionally, we present a gradient-aided coverage-maximizing stra tegy for keyframe selection that enables the selected keyframes to exhibit a clo ser focus on rich-textured regions and a broader scope for weak-textured areas.”
ZhuhaiPeople’s Republic of ChinaAsiaRobotics and AutomationRoboticsSun Yat-sen University
NETL
NSTL
