Xiaofeng Quan

TaylorMoDe-GS: Taylor-Driven Gaussian Splatting Motion Model for Multi-View Dynamic Scene Deblurring

While 3D Gaussian Splatting (3DGS) has excelled in dynamic scene reconstruction, it struggles with multi-view object motion blur, where view-dependent non-uniform blur violates fundamental multi-view geometric constraints. Existing methods fail to balance complex motion fitting with physical consist