Figure 3. Overview of the proposed all-in-focus FPM framework based on 3D implicit neural representation. (IMAGE)
Caption
The model jointly predicts 3D amplitude and phase volumes and learns a physics-informed 3D weighting map, which adaptively fuses different depth layers to produce an all-in-focus reconstruction.
Credit
Advanced Devices & Instrumentation
Usage Restrictions
News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.
License
Licensed content