公开(公告)号：US11777520B2

公开(公告)日：2023-10-03

申请号：US17218738

申请日：2021-03-31

Applicant: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITY

Inventor： Zhikang Zhang ,  Fengbo Ren ,  Kai Xu

IPC: H03M7/34 ,  H03M7/30 ,  G06N3/08 ,  G06N3/045 ,  G06N3/084 ,  G06N20/20

CPC classification number: H03M7/6047 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06N20/20

Abstract: A compression ratio (CR) adapter (CRA) for end-to-end data-driven compressive sensing (CS) reconstruction (EDCSR) frameworks is provided. EDCSR frameworks achieve state-of-the-art reconstruction performance in terms of reconstruction speed and accuracy for images and other signals. However, existing EDCSR frameworks cannot adapt to a variable CR. For applications that desire a variable CR, existing EDCSR frameworks must be trained from scratch at each CR, which is computationally costly and time-consuming. Embodiments described herein present a CRA framework that addresses the variable CR problem generally for existing and future EDCSR frameworks with no modification to given reconstruction models nor enormous additional rounds of training needed. The CRA exploits an initial reconstruction network to generate an initial estimate of reconstruction results based on a small portion of acquired image measurements. Subsequently, the CRA approximates full measurements for the main reconstruction network by complementing the sensed measurements with a re-sensed initial estimate.

公开(公告)号：US12211173B2

公开(公告)日：2025-01-28

申请号：US18045740

申请日：2022-10-11

Applicant: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITY

Inventor： Fengbo Ren ,  Kai Xu ,  Zhikang Zhang

IPC: G06T3/4046 ,  G06N3/045 ,  G06N3/084 ,  G06N20/20 ,  G06T5/50

Abstract: This disclosure addresses the single-image compressive sensing (CS) and reconstruction problem. A scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) facilitates high-fidelity, flexible and fast CS image reconstruction. LAPRAN progressively reconstructs an image following the concept of the Laplacian pyramid through multiple stages of reconstructive adversarial networks (RANs). At each pyramid level, CS measurements are fused with a contextual latent vector to generate a high-frequency image residual. Consequently, LAPRAN can produce hierarchies of reconstructed images and each with an incremental resolution and improved quality. The scalable pyramid structure of LAPRAN enables high-fidelity CS reconstruction with a flexible resolution that is adaptive to a wide range of compression ratios (CRs), which is infeasible with existing methods.

公开(公告)号：US11468542B2

公开(公告)日：2022-10-11

申请号：US16745817

申请日：2020-01-17

Applicant: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITY

Inventor： Fengbo Ren ,  Kai Xu ,  Zhikang Zhang

IPC: G06T3/40 ,  G06T5/50 ,  G06N3/08 ,  G06N20/20 ,  G06N3/04

Abstract: This disclosure addresses the single-image compressive sensing (CS) and reconstruction problem. A scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) facilitates high-fidelity, flexible and fast CS image reconstruction. LAPRAN progressively reconstructs an image following the concept of the Laplacian pyramid through multiple stages of reconstructive adversarial networks (RANs). At each pyramid level, CS measurements are fused with a contextual latent vector to generate a high-frequency image residual. Consequently, LAPRAN can produce hierarchies of reconstructed images and each with an incremental resolution and improved quality. The scalable pyramid structure of LAPRAN enables high-fidelity CS reconstruction with a flexible resolution that is adaptive to a wide range of compression ratios (CRs), which is infeasible with existing methods.