首页|Findings in Robotics and Automation Reported from Harbin Institute of Technology (Neds-slam: a Neural Explicit Dense Semantic Slam Framework Using 3d Gaussian S platting)
Findings in Robotics and Automation Reported from Harbin Institute of Technology (Neds-slam: a Neural Explicit Dense Semantic Slam Framework Using 3d Gaussian S platting)
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
New research on Robotics - Robotics an d Automation is the subject of a report. According to news reporting out of Harb in, People's Republic of China, by NewsRx editors, research stated, "We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, tha t enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in realtime. In the system, we propose a Spatially Consistent Featur e Fusion model to reduce the effect of erroneous estimates from pre-trained segm entation head on semantic reconstruction, achieving robust 3D semantic Gaussian mapping." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Youth Talent Support Program of the China.
HarbinPeople's Republic of ChinaAsiaRobotics and AutomationRoboticsHarbin Institute of Technology
NETL
NSTL
