Fig. 1. Principle of anti-scattering imaging based on deep learning. (a) Reconstruction of transmission matrix angle; (b) Speckle correlation imaging angle; (c) Optimization problem angle

Fig. 2. Different kinds of neural networks: (a) CNN^[3]; (b) RNN^[19]; (c) GAN^[9]

Fig. 3. Optimization of models based on CNN and GAN: (a) The decoder outputs dual channels for classification^[3]; (b) The decoder uses a branch structure to extract dual-target information^[20]; (c) The bottom branch of the encoder extracts features of different sizes^[23]; (d) The decoder increases attention mechanism to optimize upsampling feature weights^[25]

Fig. 4. [in Chinese]

Fig. 4. Adaptability of network: (a) Adaptively adjust the parameters of output layer²¹; (b) Adaptively adjust the weights of model²⁶

Fig. 5. Application of deep anti-scattering imaging method based on deep learning

Fig. 6. Neural network framework in different anti-scattering imaging methods. (a) Single-frame color target imaging method^[7]; (b) Imaging method through scattering media of large optical thickness^[12]; (c) Imaging method for complex objects with large field of view using a single frame speckle^[29]; (d) Imaging through scattering medium based on wavefront modulation realized by neural network^[5]

Fig. 7. An overview of the physics-aware learning framework combined with physical model and data model. (a) Physical fusion method; (b) Physical regularization method; (c) Residual physics method; (d) Embedded physics method

Fig. 8. Examples of the physics-aware learning framework combined with physical model and data model. (a) Imaging through unknown diffusers via fusing the ME prior ^[6]; (b) Imaging unknown target through scattering media via autocorrelation constraint ^[24]; (c) Untrained deep learning-based 3 D sensing method via residual physics optimization ^[51]; (d) Optimized coded-illumination for quantitative phase imaging via Physics-based learning method ^[52]