AI Paper Atlas

Research map / Image generation / Image restoration

Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks

Miika Aittala, Fredo Durand

ECCV 2018 · Image generation › Image restoration · approach: Image deblurring · 126 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
use max-pooling permutation-invariant fusion instead of recurrent frame-by-frame updateburst deblurring network · Delbracio et al. burst dataset example (c)SSIM: 0.8764 -> 0.9578Improved
use permutation-invariant network instead of Fourier burst accumulation (FBA)burst deblurring network · Delbracio et al. burst dataset example (c)SSIM: 0.9456 -> 0.9578Improved
replace max-pooling with mean-pooling in the permutation invariant layers (ablation)burst deblurring network · burst deblurringrestoration qualityNo clear effect
add correlated realistic noise model to training instead of independent Gaussian noise with std 0.02 (ablation)burst deblurring network · Figure 1 burstnoise level of outputImproved
add dynamic range expansion to training data (ablation)burst deblurring network · extremely degraded burstintensity of dark regions and streak handlingImproved
use entire burst instead of deblurring only the sharpest frame with single-image methodsburst deblurring network · self-captured noisy burstsvisual deblurring qualityImproved
train on single-image bursts only versus dedicated single-image deblurring methodsburst deblurring network · noisy vs less noisy single imagesvisual qualityMixed

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