SEHLNet: Separate Estimation of High- and Low-Frequency components for Depth Completion
Qiang Liu,Haosong Yue,Zhanggang Lyu,Wei Wang,Zhong Liu,Weihai Chen,Qiang Liu,Haosong Yue,Zhanggang Lyu,Wei Wang,Zhong Liu,Weihai Chen
Depth completion refers to inferring the dense depth map from a sparse depth map with or without corre-sponding color image. Numerous neural networks have been proposed to accomplish this task. However, insufficient uti-lization of heteromorphic data and the fact that predicted dense depth prefers a sparse depth enormously damage the performance of approaches. To reduce data preference and fully u...
