AI Paper Atlas

Research map / Image generation / Image restoration

Learning Hierarchical Line Buffer for Image Processing

Jiacheng Li, Feiran Li, Daisuke Iso

ICCV 2025 · Image generation › Image restoration · approach: Priors for restoration networks · 1 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 hierarchical line buffers instead of naive LSTM (ablation)line-buffer network · SID RAW denoising x100PSNR: 39.69 -> 41.13Improved
add more LSTM modules (ablation)LineLSTM · SID RAW denoising x100PSNR: 39.69 -> 39.94No clear effect
add progressive enhancement with channel split (ablation)LineLSTM · SID RAW denoising x100PSNR: 39.69 -> 40.87Improved
add strip-shaped convolutions (ablation)progressive-enhance LineLSTM · SID RAW denoising x100PSNR: 40.87 -> 40.98Improved
use strip convolutions instead of ordinary convolutions (ablation)full method · SID RAW denoising x100PSNR: 41.53 -> 41.69Improved
add more intra-line feature extractor blocks (ablation)full method · SID RAW denoising x100PSNR: 41.69 -> 41.91Improved
use fewer intra-line blocks (ablation)full method · SID RAW denoising x100PSNR: 41.69 -> 41.58Hurt
add the full hierarchy levels instead of fewer levels (ablation)full method · SID RAW denoising x100PSNR: 40.98 -> 41.69Improved
add inter-line design to the baseline (ablation)Baseline · SID RAW denoising x100PSNR: 40.12 -> 41.69Improved
increase lines per group from 4 to 16 (ablation)Baseline · SID RAW denoising x100PSNR: 38.78 -> 39.72Improved
increase lines per group from 4 to 16 (ablation)Ours · SID RAW denoising x100PSNR: 41.68 -> 41.89Mixed
use Ours instead of LineDLRAW denoising ELD x100 · ELD RAW denoising x100PSNR: 43.34 -> 44.38Improved

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