AI Paper Atlas

Research map / Image generation / Super-resolution

ISP2HRNet: Learning to Reconstruct High Resolution Image from Irregularly Sampled Pixels via Hierarchical Gradient Learning

Yuanlin Wang, Ruiqin Xiong, Rui Zhao, Jin Wang, Xiaopeng Fan, Tiejun Huang

ICCV 2025 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 0 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 RBF interpolation preprocessing with the full GD+GSE+IRC pipeline (ablation)ISP2HRNet · Urban100, ratio 0.2PSNR: 22.60 -> 27.43Improved
add gradient derivation (GD) before IRC (ablation)ISP2HRNet · Urban100, ratio 0.2PSNR: 26.11 -> 26.49Improved
add local gradient structure encoder (GSE) (ablation)ISP2HRNet · Urban100, ratio 0.2PSNR: 26.49 -> 27.43Improved
use content-dependent IRC instead of distance-based Gaussian weighting (ablation)ISP2HRNet · Urban100, ratio 0.2PSNR: 26.25 -> 27.43Improved
use dual-branch weight generator instead of single-branch (ablation)IRC module · Urban100, ratio 0.2PSNR: 26.92 -> 27.43Improved
use dual-branch weight generator instead of single-branch (ablation)IRC module · Urban100, ratio 0.4PSNR: 30.94 -> 31.40Improved
ISP2HRNet versus inpainting and restoration baselinesrandom missing pixel reconstruction · Urban100, ratio 0.2PSNR: 26.34 -> 27.43Improved
ISP2HRNet versus DPIR plus super-resolution pipelines at x2 and x4 on Urban100SR from incomplete image · Urban100, x2 and x4PSNR: 25.34 vs 25.69 (x2); 21.53 vs 21.74 (x4)Hurt
apply model to sampling ratios outside training distribution (x3, x4)ISP2HRNet · SR from incomplete image, DIV2K Val x4PSNR: 25.76 vs 25.74 (DPIR+SwinIR)Mixed

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