AI Paper Atlas

Research map / Point clouds / Point cloud classification

diffConv: Analyzing Irregular Point Clouds with an Irregular View

Manxi Lin, Aasa Feragen

ECCV 2022 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 18 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 masked attention (with balanced renormalization) to LS+DDBQ model (ablation)diffConv · ModelNet40OA (%): 92.2 -> 93.6Improved
add density-dilated ball query instead of constant-radius ball query (ablation)diffConv · ModelNet40OA (%): 93.1 -> 93.6Improved
add Laplacian smoothing (ablation)diffConv · ModelNet40OA (%): 92.5 -> 93.6Improved
use balanced renormalization instead of original self-attention normalization (ablation)diffConv · ModelNet40OA (%): 92.9 -> 93.6Improved
use density-dilated ball query instead of 20-NN grouping (ablation)diffConv · ModelNet40-CCER (%): 25.2 -> 21.4Improved
add masked attention instead of binary adjacency (ablation)diffConv · ModelNet40-CCER (%): 21.9 -> 21.4Improved
use masked attention instead of isotropic bias (ablation)diffConv · ModelNet40OA (%): 92.2 -> 93.6Improved
use masked attention instead of spatial distance bias (ablation)diffConv · ModelNet40OA (%): 90.2 -> 93.6Improved
use masked attention instead of inverse density bias (ablation)diffConv · ModelNet40OA (%): 89.7 -> 93.6Improved
squared radius linear dilation instead of linear radius dilation (ablation)diffConv · ModelNet40OA (%): 92.6 -> 93.6Improved
kernel density bandwidth 0.1 instead of 0.05 (ablation)diffConv · ModelNet40OA (%): 93.1 -> 93.6Improved
increase squared initial radius from 0.005 to 0.1 (ablation)diffConv · ModelNet40OA (%): 93.6 -> 91.8Hurt

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