AI Paper Atlas

Research map / Point clouds / Point cloud classification

Escape From Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

Roman Klokov, Victor Lempitsky

ICCV 2017 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 1,046 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
randomize kd-tree generation (RT instead of deterministic DT) (ablation)Kd-net depth 10 · ModelNet40accuracy: 85.7 -> 89.9Improved
randomize kd-tree generation (RT instead of DT) (ablation)Kd-net depth 10 · ModelNet10accuracy: 89.2 -> 92.8Improved
add anisotropic scaling augmentation to randomized trees (ablation)Kd-net RT depth 10 · ModelNet40accuracy: 89.9 -> 90.6Improved
add translation augmentation to randomized trees (ablation)Kd-net RT depth 10 · ModelNet40accuracy: 89.9 -> 90.1Improved
add translation augmentation on top of RT+SA (ablation)Kd-net RT+SA depth 10 · ModelNet40accuracy: 90.6 -> 90.6No clear effect
add translation augmentation on top of RT+SA (ablation)Kd-net RT+SA depth 10 · ModelNet10accuracy: 93.2 -> 93.3No clear effect
add informative leaf representations (vs constant scalar leaves) (ablation)Kd-net RT+SA depth 10 · ModelNet40accuracy: 89.8 -> 90.6Improved
add informative leaf representations (vs constant scalar leaves) (ablation)Kd-net RT+SA depth 10 · ModelNet10accuracy: 92.7 -> 93.2Improved
replace linear classifier on one-hot split directions with hierarchical Kd-network (no leaf info) (ablation)split-direction features · ModelNet40accuracy: 73.2 -> 89.8Improved
increase kd-tree depth from 10 to 15Kd-Net · ModelNet40instance accuracy: 90.6 -> 91.8Improved
increase kd-tree depth from 10 to 15Kd-Net · ModelNet10instance accuracy: 93.3 -> 94.0Improved
apply Kd-net to 20 random rotations with max-pooling (multi-view MVKd-net)Kd-net on perturbed ShapeNetCore · ShapeNetCore perturbed (micro)mAP: 0.617 -> 0.766Improved

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