AI Paper Atlas

Research map / Point clouds / Point cloud classification

SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data

Mohammad Zohaib, Alessio Del Bue

ICCV 2023 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 13 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
train with individual loss terms instead of Chamfer Distance (ablation)SC3K · KeypointNetInclusivity and Coverage: +5.02 inclusivity, +19.83 coverageImproved
add separation loss (ablation)SC3K · KeypointNetInclusivity: 63.01 -> 78.44Improved
add consistency loss (ablation)SC3K · KeypointNetDAS: 42.44 -> 74.00Improved
add pose loss (ablation)SC3K · KeypointNetmatching error: 0.095 -> 0.056Improved
add overlap loss (ablation)SC3K · KeypointNetInclusivity: 77.09 -> 78.44No clear effect
add volume loss (ablation)SC3K · KeypointNetInclusivity: 77.35 -> 78.44No clear effect
train on randomly rotated point clouds (SC3K_rot) vs canonical-pose testSC3K · KeypointNetCoverage: Inclusivity 75.89 -> 78.44, Coverage 95.63 -> 91.53Mixed

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