AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Momentum-Net: Fast and Convergent Iterative Neural Network for Inverse Problems

Il Yong Chun, Zhengyu Huang, Hongki Lim, Jeffrey A. Fessler

TPAMI 2020 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval · 107 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add extrapolation (momentum) module to Momentum-Net (ablation)Momentum-Net (sCNN) · Sparse-view CT (to reach 24 HU RMSE)MBIR time reduction (%): 53.3% less MBIR timeImproved
add extrapolation (momentum) module to Momentum-Net (ablation)Momentum-Net (sCNN) · Light-field photography from focal stack (to reach 32 dB PSNR)MBIR time reduction (%): 36.5% less MBIR timeImproved
use Momentum-Net with noniterative MBIR module instead of BCD-Net with 3 inner iterationsBCD-Net · Sparse-view CT (to reach 24 HU RMSE)MBIR time reduction (%): 62.5% less MBIR timeImproved
use Momentum-Net with noniterative MBIR module instead of BCD-Net with 3 inner iterationsBCD-Net · Light-field photography from focal stack (to reach 32 dB PSNR)MBIR time reduction (%): 61.5% less MBIR timeImproved
use deep CNN (dCNN) refiners instead of shallow CNN (sCNN) refiners (ablation)Momentum-Net · Sparse-view CT and light-field photographytotal run timeNo clear effect
use L=4 dCNN layers instead of L=6 with R=3^3 (ablation)Momentum-Net (dCNN) · Sparse-view CTRMSEImproved
use Momentum-Net instead of MBIR with learned convolutional regularizerMBIR with learned convolutional regularizer · Sparse-view CT (12.5% views)reconstruction qualityImproved
use Momentum-Net instead of MBIR with 4D EP regularizer4D EP MBIR · Light-field photography from focal stackPSNR / depth estimation accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy