Closed zjwzcx closed 2 years ago
Instead of imitating features, the network takes the soft probability distribution predicted by LiDAR-network as targets for the classification branch. For the regression, we directly use L1-loss to fit the regression offsets predicted from the LiDAR networks.
Hi Xiaoyang! Thanks for your great work. In the Introduction of LIGA-Stereo, you mentioned
Could you please elaborate on your implementation process and experimental results?