AI Paper Atlas

Research map / Image generation / Image restoration

Making the Invisible Visible: Toward High-Quality Terahertz Tomographic Imaging via Physics-Guided Restoration

Weng-Tai Su, Yi-Chun Hung, Po-Jen Yu, Shang‐Hua Yang, Chia‐Wen Lin

IJCV 2023 · Image generation › Image restoration · approach: Reflection removal · 10 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 subspace-attention fusion (SAFM) to amplitude-feature U-Net (ablation)U-Net+Amp · THz restoration, BoxPSNR (dB): 20.32 -> 21.83Improved
add subspace-attention fusion (SAFM) to amplitude-feature U-Net (ablation)U-Net+Amp · THz restoration, SkullPSNR (dB): 20.70 -> 20.18Hurt
add SAFM to phase-feature U-Net (ablation)U-Net+Phase · THz restoration, BoxPSNR (dB): 20.42 -> 21.65Improved
add SAFM when fusing amplitude and phase (ablation)SARNet · THz restoration, BoxPSNR (dB): 20.00 -> 22.67Improved
add SAFM when fusing amplitude and phase (ablation)SARNet · THz restoration, SkullPSNR (dB): 21.18 -> 22.48Improved
add subspace projection to SARNet (ablation)SARNet · THz restoration, BoxPSNR (dB): 21.43 -> 22.67Improved
add multi-view inter-view fusion to SARNet (ablation)SARNet · THz restoration, BoxPSNR (dB): 22.67 -> 23.23Improved
add multi-view inter-view fusion to SARNet (ablation)SARNet · THz restoration, SkullPSNR (dB): 22.48 -> 23.05Improved
add multi-spectral amplitude features without SAFM to U-Net (ablation)U-Net · THz restoration, BoxPSNR (dB): 19.77 -> 20.32Improved
combine amplitude and phase directly without SAFM instead of amplitude only (ablation)SARNet w/o SAFM · THz restoration, BoxPSNR (dB): 20.32 -> 20.00Hurt
add SAFM to multi-view model (ablation)SARNet_MV · THz restoration, BoxPSNR (dB): 22.10 -> 23.23Improved
use SARNet_MV instead of NBNetSARNet_MV · THz restoration, averagePSNR (dB): +2.23 dBImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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