He Guan1,2, Chuanchen Luo1, Lue Fan1,2, Junran Peng1, Zhaoxiang Zhang1,2,3,4, 1Institute of Automation, Chinese Academy of Sciences 2University of Chinese Academy of Sciences (UCAS) 3Centre for Artificial Intelligence and Robotics (HKISI, CAS) 4State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Abstract The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively trainin...