AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees

Jun-Kun Chen, Yu-Xiong Wang

ECCV 2022 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 4 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
use relaxed PCA-based K-D tree instead of the original axis-aligned K-D tree (ablation)PointTree Def · ModelNet40 affine (with PA)overall accuracy (%): 82.7 -> 68.8 when replaced with original K-D treeImproved
merge child info with pointwise maximum instead of concatenate-MLP (ablation)PointTree RNS · ModelNet40 affine (with PA)overall accuracy (%): 84.1 -> 79.3 with concatenate-MLPImproved
add the learnable alignment network (ablation)PointTree Def · ModelNet40 affine (with PA)overall accuracy (%): 82.4 -> 82.7Improved
use stronger K-D tree alignment network (KA) rather than T-Net (Def) (ablation)PointTree · ModelNet40 affine (with PA)overall accuracy (%): 82.7 -> 83.4Improved
use ResNet-style stacked encoder (RNS) rather than Def (ablation)PointTree · ModelNet40 affine (with PA)overall accuracy (%): 82.7 -> 84.1Improved
add PCA pre-alignment (ablation)PointTree RNS · ModelNet40 affineoverall accuracy (%): 73.1 -> 84.1Improved
add PCA pre-alignment (ablation)PointTree Def · ModelNet40 affineoverall accuracy (%): 70.2 -> 82.7Improved
add PCA pre-alignment to baselinesPointNet, DGCNN, PointMLP and other baselines · ModelNet40 affineoverall accuracy (%): at least 10% improvement in accuracyImproved
add pre-alignment to baselinesDGCNN · ModelNet40 projectiveoverall accuracy (%): 6.2 -> 47.3Improved
replace PointNet-style MLP/ball clustering with relaxed K-D tree design (PointTree RNS vs 3DContextNet)PointTree RNS · ModelNet40 affineoverall accuracy (%): 76.7 -> 84.1 with PA; 37.1 -> 73.1 without PAImproved
PD-Net coordinate-dependent aggregation vs PointTree aggregationPD-Net · ModelNet40 affine (with PA)overall accuracy (%): 62.0 vs 84.1Hurt
apply PointTree encoder to ShapeNetPart part segmentationPointTree RNS · ShapeNetPart affine (with PA)class mIoU (%): 71.7 -> 78.7 vs GDANetImproved

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