AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings

Sara Shaheen, Lama Affara, Bernard Ghanem

ICCV 2017 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees · 10 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
constrain CSC filters to cubic Bezier curves (vs standard CSC)Convolutional sparse coding · Line drawingsPSNR (dB): 40 -> 29Hurt
add the parametric projection inside ADMM instead of fitting curves to standard CSC filters afterwards (ablation)Constrained parametric CSC · Line drawingsPSNR (dB): 11 -> 29; 18dB lower when fitted after trainingImproved
increase sparsity coefficient beta (ablation)Constrained parametric CSC · Line drawingsgeometric representativeness vs reconstruction quality: beta = 0.6 chosenMixed
initialize filters closer to actual strokes (ablation)Constrained parametric CSC · Line drawingsconvergence speed and reconstruction 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