Fig. 1. Neural network architecture

Fig. 2. Label of neural network

Fig. 3. Image data captured by stereo system. (a) Measured object pattern; (b) high-frequency fringe pattern; (c) speckle pattern from left camera; (d) speckle pattern from right camera

Fig. 4. Training data captured by left camera and the absolute phase calculated by fringe patterns

Fig. 5. Disparity map and error graph from true value. (a) Disparity of ZNCC matching; (b) disparity of CNN; (c) disparity of the proposed method; (d) error of ZNCC matching; (e) error of CNN; (f) error of the proposed method; (g) depth of ZNCC matching; (h) depth of CNN; (i) depth of the proposed method

Fig. 6. Measured object and 3D reconstruction result. (a), (c), (e) measured object; (b), (d), (f) 3D reconstruction result

Fig. 7. 3D reconstruction and analysis of precision sphere. (a) 3D reconstruction result of left precision sphere; (b) error distribution of left precision sphere; (c) error histogram of left precision sphere; (d) 3D reconstruction result of right precision sphere; (e) error distribution of right precision sphere; (f) error histogram of right precision sphere