AI Paper Atlas

Research map / Image generation / Image restoration

Iterative Residual CNNs for Burst Photography Applications

CVPR 2019 · Image generation › Image restoration · approach: Image harmonization and color transformation · 29 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
use the model's burst-aware iterative reconstruction instead of the strongest listed baselineINN · MSR demosaicking, noisy and noise-free linRGB/sRGBPSNR: performance gains ranging from 0.9 to 1.5 dBHelped
use INN rather than the best competing baseline at each tested noise levelINN · Waterloo burst denoising, σ=10, σ=15, σ=20, and σ=25PSNR: 38.71 vs 37.65; 37.36 vs 36.06; 36.24 vs 34.89; 35.28 vs 33.86Helped
use INN rather than the best competing baselineINN · Waterloo burst denoising, σ=5PSNR: 40.08 vs 40.19Hurt
use oracle warping matrices instead of ECC-estimated alignment (ablation)INN · MSR burst demosaickingPSNR: up to 1.9 dBsHelped
train with 4 or 8 frames and evaluate on longer bursts (ablation)INN · Waterloo burst denoising, burst sizes 2 to 16PSNRHelped
train with 2 frames and evaluate beyond a certain burst size (ablation)INN · Waterloo burst denoising, burst sizes 2 to 16PSNRHurt

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