Wire Arc Additive Manufacturing (WAAM) has developed rapidly in recent years and has been widely used in industry. Cold Metal Transfer (CMT), a kind of Gas Metal Arc Welding (GMAW), is widely used in the modeling of thin parts. In the monitoring of CMT process, it is necessary to monitor the weld reinforcement of the deposited layer. It can provide effective alerting for welding and help to improve welding quality. In this paper, the weld reinforcement and the position of molten pool image on the deposited layer are determined by the molten pool visual acquisition system. According to the data of the same direction additive manufacturing experiment, the future molten pool image is predicted by the improved prediction network (PredNet). Meanwhile through a regression network (SERes), the predicted results are regressed to the accurate weld reinforcement information of the deposited layer in advance. The experimental results show that the monitoring system designed in this paper can predict the change of molten pool shape 140ms in advance and the average precision of the weld reinforcement regression is better than 0.3mm. This paper provides the necessary basis for the shape on-line monitoring and controlling in WAAM process.

Deep learning-based fringe projection profilometry (FPP) shows potential for challenging three-dimensional (3D) reconstruction of objects with dynamic motion, complex surface, and extreme environment. However, the previous deep learning-based methods are all supervised ones, which are difficult to be applied for scenes that are different from the training, thus requiring a large number of training datasets. In this paper, we propose a new geometric constraint-based phase unwrapping (GCPU) method that enables an untrained deep learning-based FPP for the first time. An untrained convolutional neural network is designed to achieve correct phase unwrapping through a network parameter space optimization. The loss function of the optimization is constructed by following the 3D, structural, and phase consistency. The designed untrained network directly outputs the desired fringe order with the inputted phase and fringe background. The experiments verify that the proposed GCPU method provides higher robustness compared with the traditional GCPU methods, thus resulting in accurate 3D reconstruction for objects with a complex surface. Unlike the commonly used temporal phase unwrapping, the proposed GCPU method does not require additional fringe patterns, which can also be used for the dynamic 3D measurement.

Atmospheric scattering caused by suspended particles in the air severely degrades the scene radiance. This paper proposes a method to remove haze by using a neural network that combines scene polarization information. The neural network is self-supervised and online globally optimization can be achieved by using the atmospheric transmission model and gradient descent. Therefore, the proposed method does not require any haze-free image as the constraint for neural network training. The proposed approach is far superior to supervised algorithms in the performance of dehazing and is highly robust to the scene. It is proved that this method can significantly improve the contrast of the original image, and the detailed information of the scene can be effectively enhanced.

The three-dimensional (3D) memory effect (ME) has been shown to exist in a variety of scattering scenes. Limited by the scope of ME, speckle correlation technology only can be applied in a small imaging field of view (FOV) with a small depth of field (DOF). In this Letter, an untrained neural network is constructed and used as an optimization tool to restore the targets beyond the 3D ME range. The autocorrelation consistency relationship and the generative adversarial strategy are combined. Only single frame speckle and unaligned real targets are needed for online optimization; therefore, the neural network does not need to train in advance. Furthermore, the proposed method does not need to conduct additional modulation for the system. This method can reconstruct not only hidden targets behind the scattering medium, but also targets around corners. The combination strategy of the generative adversarial framework with physical priors used to decouple the aliasing information and reconstruct the target will provide inspiration for the field of computational imaging.