AI Paper Atlas

Research map / Point clouds / Point cloud classification

HHA: Hierarchical Hyperbolic Constraints for Imperceptible Point Cloud Attacks

Keke Tang, Yu Liao, Weilong Peng, Xiaofei Wang, Daizong Liu, Zhongyun Hua, Peican Zhu, Zhihong Tian

ECCV 2026 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 0 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 hierarchical hyperbolic regularization (full HHA) vs best baseline LBCHHA · ModelNet40 PointNetCD (1e-4): 0.897 -> 0.603Improved
add hierarchical hyperbolic regularization vs LBCHHA · ScanObjectNN PointNetCD (1e-4): 0.879 -> 0.474Improved
add semantic regularization to geometric-only (ablation)HHA · ModelNet40 PointNetCD (1e-4): 0.686 -> 0.603Improved
add geometric regularization to semantic-only (ablation)HHA · ModelNet40 PointNetCD (1e-4): 0.621 -> 0.603Improved
add semantic regularization to geometric-only (ablation)HHA · ScanObjectNN PointNetCD (1e-4): 0.510 -> 0.474Improved
use hyperbolic distance instead of Euclidean in component regularization (ablation)HHA · ModelNet40 PointNetCD (1e-4): 1.034 -> 0.603Improved
use hyperbolic distance instead of Euclidean in component regularization (ablation)HHA · ModelNet40 PointNetHD (1e-2): 0.511 -> 0.279Improved
increase curvature c from 0.01 to 1.0 (ablation)HHA · ModelNet40 PointNetCD (1e-4): 0.805 -> 0.603Improved
increase curvature c from 1.0 to 1.5 (ablation)HHA · ModelNet40 PointNetCD (1e-4): 0.603 -> 0.757Hurt
use Poincare ball model instead of Lorentz model (ablation)HHA · ModelNet40 PointNetCD (1e-4): 2.108 -> 0.603Improved
use stronger P3-SAM segmenter instead of PartSLIP (ablation)HHA · ScanObjectNN PointNetCD (1e-4): 0.474 -> 0.469No clear effect
attack with HHA under IF-Defense instead of LBCHHA · ModelNet40 PointNetASR (%): 45.2 -> 75.7Improved

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