AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Alexandre Carlier, Martin Danelljan, Alexandre Alahi, Radu Timofte

NeurIPS 2020 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 30 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
Replace autoregressive command prediction with feed-forward prediction (ablation)One-stage SVG autoencoder · SVG-Icons8RE: 0.102 / 0.170 -> 0.007 / 0.014Improved
Replace autoregressive command prediction with feed-forward prediction (ablation)One-stage SVG autoencoder · SVG-Icons8IS: 0.25 / 0.36 -> 0.12 / 0.17Improved
Add hierarchical path-level encoding and decoding (ablation)One-stage feed-forward SVG autoencoder · SVG-Icons8 interpolation human study1st rank votes (%): 19.5 -> 44.8Improved
Replace Hungarian path assignment with ordered path assignment (ablation)DeepSVG · SVG-Icons8IS: 0.09 / 0.14 -> 0.08 / 0.12Improved

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