AI Paper Atlas

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

PSyCo: Manifold Span Reduction for Super Resolution

CVPR 2016 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval · 56 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Collapse patch variations using dihedral and antipodal symmetry (ablation)PSyCo · Set14 ×2PSNR: around 0.4 dB higher for small dictionary sizesHelped
Collapse patch variations using dihedral and antipodal symmetry (ablation)PSyCo · Set14 ×2PSNR: around 0.2 dB for 1024 atomsHelped
Collapse antipodal symmetry (ablation)PSyCo · Set14 ×2PSNRHelped
Collapse dihedral symmetries together (ablation)PSyCo · Set14 ×2PSNRHelped
Use a larger neighborhood size (ablation)PSyCo · Set14 ×2PSNRMixed
Vary the regularization weight λ (ablation)PSyCo · Set14 ×2PSNRNo clear effect
Use PSyCo with 1024 atoms rather than A+Super-resolution benchmark datasets · Set5, Set14, Kodak, Urban100; ×2, ×3, ×4PSNR: around 0.3dB higher across all s and datasetsHelped
Use PSyCo with 32 atomsSuper-resolution inference · Benchmark datasetsexecution time: an order of magnitude fasterHelped

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