AI Paper Atlas

Research map / Image generation / Image restoration

Deep Burst Denoising

Clement Godard, Kevin Matzen, Matt Uyttendaele

ECCV 2018 · Image generation › Image restoration · approach: Raw and low-light noise modeling · 128 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 recurrent two-track multi-frame network instead of concatenating 8 frames (ablation)Concat C8F · Live Photos ablation, AWGN sigma=50, 8-frame trainingPSNR (dB): 32.15 -> 33.62Improved
use recurrent network instead of concatenating 2 frames (ablation)Concat C2F · Live Photos ablation, AWGN sigma=50, 8-frame trainingPSNR (dB): 30.89 -> 33.62Improved
add stabilization of burst before denoising (ablation)Ours · Live Photos ablation, AWGN sigma=50, 8-frame trainingPSNR (dB): 32.60 -> 33.62Improved
increase depth from 8 to 12 layers (ablation)Ours 8L · Live Photos ablation, AWGN sigma=50, 8-frame trainingPSNR (dB): 33.62 -> 33.80Improved
increase depth from 8 to 16 layers (ablation)Ours 8L · Live Photos ablation, AWGN sigma=50, 8-frame trainingPSNR (dB): 33.62 -> 33.35Hurt
increase depth from 8 to 20 layers (ablation)Ours 8L · Live Photos ablation, AWGN sigma=50, 8-frame trainingPSNR (dB): 33.62 -> 33.48Hurt
reduce depth from 8 to 4 layers (ablation)Ours 8L · Live Photos ablation, AWGN sigma=50, 8-frame trainingPSNR (dB): 33.62 -> 33.01Hurt
pre-train single-frame track before multi-frame training (ablation)Ours MFD · Live Photos, AWGN sigma=50PSNR (dB): 0.5dB leadImproved
train on 8-frame sequences instead of 2 or 4 frames (ablation)Ours MFD · Live Photos, 16-frame testgeneralization to longer sequencesImproved
feed sequence forward then backward at test time (ablation)Ours MFD · Live Photosburn-in and flickeringImproved
use multi-frame recurrent network instead of single-frame DenoiseNet, sigma=50DenoiseNet · Live Photos multi-frame (16-frame test seqs), AWGN sigma=50PSNR (dB): 29.56 -> 33.62Improved
use multi-frame network instead of VBM4D, sigma=75VBM4D · Live Photos multi-frame (16-frame test seqs), AWGN sigma=75PSNR (dB): 26.60 -> 31.44Improved

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