Fig. 1. Architecture overview of PSMnet

Fig. 2. Architecture overview of proposed algorithm

Fig. 3. Location-based channel attention module

Fig. 4. Multi-cross-attention module

Fig. 5. Attention hourglass module

Fig. 6. Comparison of ReLU function and Mish function

Fig. 7. Parallax evaluation results on KITTI2015 test set. (a1) (a3) Left images; (a2) (a4) partial enlargement of left images; (b1) (b3) disparity maps predicted by PSMnet; (b2) (b4) partial enlargement of disparity maps; (c1) (c3) the corresponding error maps; (c2) (c4) local enlargement of the corresponding error maps; (d1) (d3) disparity maps predicted by MAnet; (d2) (d4) partial enlargement of disparity maps; (e1) (e3) the corresponding error maps; (e2) (e4) partial enlargement of the corresponding error maps

Table 1. Performance evaluation of different algorithms on the KITTI2015 test set

Table 2. Performance evaluation of different algorithms on the KITTI2012 test set