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. 3. Samples from our collected datasets.

Fig. 3.

All our experiments are conducted on real data captured using lensless prototypes. We collect Display Captured Dataset using both separable and non-separable prototypes to train FlatNet-sep and FlatNet-gen, respectively. We also collect Direct Captured Dataset by placing objects in front of the lensless cameras under controlled illumination. Finally, to improve the robustness of FlatNet, we collect a dataset of Unconstrained Indoor Scenes using PhlatCam and Webcam pairs.