AI Paper Atlas

Research map / Image generation / Image restoration

Seeing through a Black Box: Toward High-Quality Terahertz Imaging via Subspace-and-Attention Guided Restoration

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

ECCV 2022 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 4 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 multi-band amplitude features to U-Net (no SAFM) (ablation)U-Netbase · THz restoration, DeerPSNR (dB): 19.84 -> 22.05Improved
add multi-band phase features to U-Net (no SAFM) (ablation)U-Netbase · THz restoration, DeerPSNR (dB): 19.84 -> 21.14Improved
concatenate phase with amplitude directly instead of amplitude only (no SAFM) (ablation)Amp-Unet w/o SAFM · THz restoration, DeerPSNR (dB): 22.05 -> 21.44Hurt
add SAFM to amplitude-only network (ablation)Amp-Unet · THz restoration, DeerPSNR (dB): 22.05 -> 20.97Mixed
add SAFM to phase-only network (ablation)Phase-Unet · THz restoration, DeerPSNR (dB): 21.14 -> 22.66Improved
add SAFM fusion of amplitude and phase (full SARNet) (ablation)Mix-Unet · THz restoration, DeerPSNR (dB): 21.44 -> 22.98Improved
add phase features to SAFM amplitude network (full SARNet) (ablation)Amp-Unet w/ SAFM · THz restoration, BoxPSNR (dB): 21.83 -> 22.67Improved
replace U-NetMB with SARNetU-NetMB · THz restoration, 7 objects averagePSNR (dB): 1.51 dBImproved
replace U-Netbase with SARNetU-Netbase · THz restoration, 7 objects averagePSNR (dB): 2.86 dBImproved
replace Time-max with SARNet restorationTime-max · THz restoration, 7 objects averagePSNR (dB): 11.17 dBImproved
replace U-NetMB with SARNetU-NetMB · THz restoration, 7 objects averageSSIM: 0.072Improved
replace U-NetMB with SARNet before inverse Radon reconstructionU-NetMB · THz 3D tomography, DeerMSE of cross-sections: 0.183 -> 0.107Improved

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