Fig. 1. Experiment setup

Fig. 2. Schematic diagram of multi-scale fusion network structure based on attention module

Fig. 3. (a) The input intensity map; (b) The input depth map; (c) The result processed by MLE method; (d) The result processed by He et al. ^[16]; (e) The result processed by Lindell et al. ^[10]; (f) The result processed by proposed method in this paper

Fig. 4. (a) Network input intensity map; (b) The result of the method proposed in the paper; (c) The result processed by the network without attention module; (d) The result processed by the network without intensity guidance; (e) The result processed by the network of loss function without ordinal regression loss; (f) The result processed by the network without KL divergence

Fig. 5. (a) Point cloud without upsampling; (b) Point cloud with post-upsampling method; (c) Point cloud with pre-upsampling method