atlas

Research map / Point clouds / Point cloud classification

Cloud2Curve: Generation and Vectorization of Parametric Sketches

CVPR 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 28 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
add MSE loss to SWD (ablation)Cloud2Curve vectorization · Quick, Draw!test loss: 0.00123 -> 0.00034Helped
add MSE loss to SWD (ablation)Cloud2Curve vectorization · KMNISTtest loss: 8.4\cdot 10^{-3} -> 2.1\cdot 10^{-4}Helped
increase λd from 10⁻³ to 10⁻² (ablation)Cloud2Curve vectorization · Quick, Draw!classification accuracy: 0.80 -> 0.69Hurt
increase λd from 10⁻³ to 10⁻² (ablation)Cloud2Curve vectorization · KMNISTclassification accuracy: 0.82 -> 0.73Hurt
use point-cloud rather than sequence supervisionBézierSketch · Quick, Draw!classification accuracy: 0.86 -> 0.41Hurt
use Cloud2Curve point-cloud vectorization instead of BézierSketch with cloud dataQuick, Draw! vectorization · Quick, Draw!classification accuracy: 0.41 -> 0.80Helped

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