AI Paper Atlas

Research map / Image generation / Image restoration

Consensus Convolutional Sparse Coding

Biswarup Choudhury, Robin Swanson, Felix Heide, Gordon Wetzstein, Wolfgang Heidrich

ICCV 2017 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 42 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
solve CSC as a consensus problem over blocks (CCSC, 10 workers) instead of global CSCconvolutional sparse coding · 2D dataset of 500 imagesruntime (sec): 1530.71 sec -> 82.69 secImproved
increase parallel workers from 10 to 50 in CCSC (ablation)CCSC · 2D dataset of 500 imagesruntime (sec): 82.69 sec -> 28.57 secImproved
use CCSC instead of global CSC on 1000 imagesconvolutional sparse coding · 2D dataset of 1000 imagesfeasibility: Out of Memory -> 387.68 secImproved
use CCSC (5 workers) at 100 imagesconvolutional sparse coding · 2D dataset of 100 imagesruntime (sec): 203.56 sec -> 35.35 secImproved
split the CSC problem into consensus subproblems (ablation)CCSC · iteration countiterations neededHurt
use CCSC large-scale ImageNet dictionary for inpainting versus conventional CSCCCSC · 2D inpainting, Wind MillPSNR (dB): 33.49 -> 35.13Improved
use CCSC dictionary for Poisson deconvolution versus conventional CSCCCSC · 2D Poisson deconvolution, PorschePSNR (dB): 26.21 -> 27.11Improved
use CCSC for multispectral demosaicing versus IIDCCSC · 3D multispectral demosaicing, ClayPSNR (dB): 14.25 -> 29.74Improved
use CCSC for light field view synthesis versus KalantariCCSC · Light field view synthesis, CarsPSNR (dB): 21.41 -> 27.57Improved
train dictionary on 5000 ImageNet images instead of a very small fruit dataset (ablation)CCSC · reconstructionreconstruction qualityImproved
learn multispectral dictionary with shared coefficients across channels instead of solving each channel individually with 2D CSC (ablation)CCSC · multispectral datareconstruction qualityImproved

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