AI Paper Atlas

Research map / Image generation / Super-resolution

Light Field Super-Resolution using a Low-Rank Prior and Deep Convolutional Neural Networks

Reuben A. Farrugia, Christine M. Guillemot

TPAMI 2019 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 65 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 iterative back-projection post-processing (ablation)LR-LFSR · Bee 2 (INRIA) x2 SRPSNR: 33.4915 -> 35.0306Improved
add iterative back-projection post-processing (ablation)LF-SRCNN · Bee 2 (INRIA) x2 SRPSNR: 33.8268 -> 34.7257Improved
add iterative back-projection post-processing (ablation)LR-LFSR · Chess (STANFORD) x3 SRPSNR: 30.1485 -> 31.4388Improved
IBP applied to both methods widens the gap between LR-LFSR and LF-SRCNN (ablation)LR-LFSR vs LF-SRCNN · INRIA and Stanford light fieldsPSNR: 0.23 dB and 0.12 dB without IBP, roughly doubles with IBP (0.41 dB and 0.31 dB)Improved
LR-LFSR vs second-best LF-SRCNN, no IBPLR-LFSR · INRIA and Stanford light fieldsPSNR: 0.2 dB gainImproved
LR-LFSR with IBP vs LF-SRCNN with IBPLR-LFSR-IBP · INRIA and Stanford light fieldsPSNR: +0.41 dB at x2, +0.31 dB at x3Improved
per-view single-image SR (VDSR) vs bicubicVDSR · INRIA and Stanford light fieldsPSNR: +0.33 dB over bicubicImproved
add block-matching alignment to PCA+RRPCA+RR · INRIA and Stanford light fieldsPSNR: 2.52 dB and 1.76 dB over bicubicImproved
LF-SRCNN vs BM+PCA+RRLF-SRCNN · INRIA and Stanford light fieldsPSNR: marginal gain 0.05 dBNo clear effect
no disparity compensation (PCA+RR) on large-disparity Stanford light fieldsPCA+RR · Bracelet (STANFORD) x2 SRPSNR: 23.8183 vs bicubic 26.4662Hurt
LR-LFSR vs PCA+RR on small-disparity INRIALR-LFSR · Bee 2 (INRIA) x2 SRPSNR: 33.4915 vs PCA+RR 34.1579Hurt

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