Fig. 1. Model structure

Fig. 2. Encoder structure and encoding process

Fig. 3. Decoder structure and decoding process

Fig. 4. AdaBins module structure and processing process

Fig. 5. Prediction results of different models. (a) Input RGB images; (b) ground truth depth maps; (c) depth map predicted by model in literature [7]; (d) depth map predicted by model in literature [11]; (e) depth map predicted by proposed model

Fig. 6. Examples of proposed model generating a three-dimensional point cloud from a single RGB image

Fig. 7. Ablation study of different loss functions. (a) Comparison of using Lbins or not; (b)(c)(d) comparison of using Lbins combined with different loss items and weight values

Fig. 8. Ablation study of different encoders

Fig. 9. Ablation study of different initialization methods

Fig. 10. Ablation study of AdaBins module