AI Paper Atlas

Research map / Image generation / Image restoration

Probabilistic-Based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising

Xianqiang Lyu, Junhui Hou

IJCV 2024 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 14 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 probabilistic modeling (vs template network) (ablation)CR-Net · HCI+Inria S=2PSNR: 42.12 -> 42.49Improved
add PFE instead of 3-D convolution (ablation)CR-Net · HCI+Inria S=2PSNR: 40.42 -> 42.49Improved
add PFE instead of SAS layers (ablation)CR-Net · HCI+Inria S=2PSNR: 41.11 -> 42.49Improved
share projection layer weights across stages (ablation)CR-Net · HCI+Inria S=2PSNR: 41.67 -> 42.49Improved
increase stages T from 2 to 6 (ablation)CR-Net · HCI+Inria S=2PSNR: 41.53 -> 42.49Improved
increase feature embedding units J from 8 to 10 (ablation)CR-Net · HCI+Inria S=2PSNR: 42.49 -> 41.91Hurt
increase feature embedding units J from 6 to 8 (ablation)CR-Net · HCI+Inria S=2PSNR: 41.55 -> 42.49Improved
add noise suppression module (ablation)DN-Net · HCI+Inria sigma=20PSNR: 40.04 -> 40.50Improved
add PFE instead of SAS layers (ablation)DN-Net · HCI+Inria sigma=20PSNR: 38.82 -> 40.50Improved
add PFE instead of 3-D convolution (ablation)DN-Net · HCI+Inria sigma=20PSNR: 36.82 -> 40.50Improved
add probabilistic modeling (vs template network) (ablation)DN-Net · HCI+Inria sigma=20PSNR: 40.27 -> 40.50Improved
increase iterative stages T from 1 to 4 (ablation)DN-Net · HCI+Inria sigma=20PSNR: 40.01 -> 40.76Improved

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