AI Paper Atlas

Research map / Image generation / Super-resolution

Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT

Aujasvit Datta, Jiayun Wang, Asad Aali, Anima Anandkumar

ECCV 2026 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 2 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
replace regular convolutions with DISCO neural operators in unrolled network (ablation)CTO · AAPM abdomen CT, 18-viewPSNR: 29.14 -> 31.57Improved
train one model on all sampling rates instead of rate-specific training (ablation)LEARN · AAPM abdomen CT, 18-viewPSNR: 4.16 -> 25.51Improved
train one model on all sampling rates instead of 72-view only (ablation)LEARN · AAPM abdomen CT, 72-viewPSNR: 32.32 -> 29.90Hurt
add flipped circular padding along view angle (rotation equivariance) (ablation)CTO · 24-view reconstructionPSNR: 32.17 -> 33.00Improved
add sinogram-space operator N_s (ablation)CTO · sparse-view CT averaged over view countsPSNR: 4.82 dB drop when removedImproved
add image-space operator N_i (ablation)CTO · sparse-view CT averaged over view countsPSNR: 3.86 dB drop when removedImproved
add spatial branch in N_s (ablation)CTO · sparse-view CTPSNR: 3.1 dB drop when removedImproved
add frequency branch in N_s (ablation)CTO · sparse-view CTPSNR: 2.7 dB drop when removedImproved
apply Fourier transform along detector axis in N_s,freq vs no transform (ablation)CTO · sparse-view CTPSNR: 2.7 dB gainImproved
use Morlet or Zernike DISCO basis instead of piecewise linear (ablation)CTO · DISCO hyperparameter searchvalidation PSNRHurt
CTO vs diffusion DPS on inference speedCTO · AAPM abdomen CTinference time: 51.58 s -> 0.065 sImproved
zero-shot 2x image resolution testCTO · AAPM 18-view 256 to 512PSNR: +3 dB over CNN baselineImproved

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