AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images

Zhetong Liang, Shi Guo, Hong Gu, Huaqi Zhang, Lei Zhang

ECCV 2020 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 11 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 two separate instances of PreP and PostP modules (decoupled) instead of shared modules in alternating training (ablation)BDNet · Real-staticPSNR/SSIM: 44.67/0.967 -> 45.31/0.971Improved
use decoupled alternating training instead of train on Dd then fine-tune on Ds (ablation)BDNet · Real-staticPSNR/SSIM: 45.17/0.968 -> 45.31/0.971No clear effect
use decoupled learning instead of fine-tuning on static data (perceptual quality, dynamic scenes) (ablation)BDNet · Real-dynamicvisual qualityImproved
use BDNet with decoupled learning instead of KPNburst denoising · Vimeo-200 synthetic G50PSNR/SSIM: 32.44/0.862 -> 34.03/0.900Improved
use BDNet instead of RIDNetburst denoising · Vimeo-200 synthetic PGPSNR/SSIM: 38.34/0.954 -> 39.45/0.965Improved
use BDNet instead of TOFlowburst denoising · Vimeo-200 synthetic G25PSNR/SSIM: 34.99/0.902 -> 36.78/0.937Improved
increase noise level from G25 to G50 for image-domain alignment (TOFlow)TOFlow · Vimeo-200 syntheticPSNR: 34.99 -> 31.95Hurt
make single-frame models multi-frame with optical flow alignment and average fusion (M-UNet vs UNet)UNet · Real-staticPSNR/SSIM: 43.85/0.954 -> 44.23/0.964Improved
make RIDNet multi-frame with optical flow alignment and average fusion (M-RIDNet vs RIDNet)RIDNet · Real-staticPSNR/SSIM: 44.17/0.960 -> 44.54/0.968Improved
use BDNet instead of INNburst denoising · Real-staticPSNR/SSIM: 43.95/0.964 -> 45.31/0.971Improved
train on synthetic data only (KPN) instead of adapting to real static dataKPN · Real-staticPSNR/SSIM: 39.68/0.867Hurt

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