GS-ASM: 2DGS-Supervised Active Stereo Matching
A novel framework is proposed that synthesizes proxy labels to enable supervised training of deep active stereo networks without requiring any ground-truth depth, and develops an active 2D Gaussian Splatting- based synthesis method that explicitly models the scene geometry and the projected active pattern.
Zhengling Wu, Rongfeng Lu, Quan Chen et al.
· 0 citations