AI Paper Atlas

Research map / Point clouds / Point cloud classification

Dynamic Points Agglomeration for Hierarchical Point Sets Learning

Jinxian Liu, Bingbing Ni, Caiyuan Li, Jiancheng Yang, Qi Tian

ICCV 2019 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 116 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
add parameter sharing with part division (8-4-1 instead of 1-1-1) (ablation)Dynamic points agglomeration · ModelNet40instance accuracy (%): 90.9 -> 91.9Improved
merge parts gradually (4-2-1 instead of constant 8-8-8) (ablation)Dynamic points agglomeration · ModelNet40instance accuracy (%): 91.2 -> 91.7Improved
add T-Net to the model (ablation)Dynamic points agglomeration · ModelNet40instance accuracy (%): 91.4 -> 91.9Improved
divide input along x-axis instead of randomly (ablation)Dynamic points agglomeration · ModelNet40instance accuracy (%): 90.9 -> 91.9Improved
choose z-axis instead of x-axis for division (ablation)Dynamic points agglomeration · ModelNet40instance accuracy (%): 91.9 -> 91.8No clear effect
choose y-axis instead of x-axis for division (ablation)Dynamic points agglomeration · ModelNet40instance accuracy (%): 91.9 -> 91.6No clear effect
add T-Net to the model (cost) (ablation)Dynamic points agglomeration · ModelNet40inference time (ms): 18.4 -> 36.6Hurt
use learned agglomeration versus PointNet++ under Gaussian noiseDynamic points agglomeration · ModelNet40 noise robustnessaccuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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