Skip to main content
. Author manuscript; available in PMC: 2023 Apr 1.
Published in final edited form as: IEEE Trans Pattern Anal Mach Intell. 2022 Mar 4;44(4):1934–1948. doi: 10.1109/TPAMI.2020.3033882

Fig. 2. Overall architecture of the FlatNet.

Fig. 2.

The lensless camera measurement is first mapped into an intermediate image space using a trainable camera inversion layer. This stage is implemented separately for the separable and the non-separable case. A U-Net [31] then enhances the perceptual quality of the intermediate reconstruction. We use a weighted combination of three losses in training our network: a perceptual loss [32] using a VGG16 network [33], mean-square error (MSE), and adversarial loss using a discriminator neural network [34].