US 12,073,578 B2
Passive and single-viewpoint 3D imaging system
Yicheng Wu, Houston, TX (US); Vivek Boominathan, Houston, TX (US); Huaijin Chen, Houston, TX (US); Aswin C. Sankaranarayanan, Pittsburgh, PA (US); and Ashok Veeraraghavan, Houston, TX (US)
Assigned to William Marsh Rice University, Houston, TX (US); and Carnegie Mellon University, Pittsburgh, PA (US)
Filed by William Marsh Rice University, Houston, TX (US); and Carnegie Mellon University, Pittsburgh, PA (US)
Filed on Apr. 26, 2023, as Appl. No. 18/307,387.
Application 18/307,387 is a continuation of application No. 16/865,229, filed on May 1, 2020, granted, now 11,676,294.
Claims priority of provisional application 62/841,566, filed on May 1, 2019.
Prior Publication US 2023/0410341 A1, Dec. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/55 (2017.01); H04N 13/111 (2018.01); H04N 13/122 (2018.01); H04N 13/128 (2018.01); H04N 13/229 (2018.01)
CPC G06T 7/55 (2017.01) [H04N 13/111 (2018.05); H04N 13/122 (2018.05); H04N 13/128 (2018.05); H04N 13/229 (2018.05); G06T 2200/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for a passive single-viewpoint 3D imaging system, comprising:
capturing an image from a camera, the camera having one or more phase masks;
using a reconstruction algorithm, for estimation of a 3D or depth image,
wherein the reconstruction algorithm comprises:
building a differentiable forward model with an optical layer and a reconstruction network,
wherein in the optical layer, a physics-based model simulates a coded image captured on a sensor with a phase mask, and
wherein in the reconstruction network, a neural network produces a depth map from the coded image.