AI Paper Atlas

Research map / Point clouds / Point cloud classification

Primary Visual Cortex Inspired Point Cloud Analysis Framework

Jisheng Dang, Delin Deng, Bimei Wang, Jingze Wu, Hui Zhang, Haijiang Li, Jingmei Jiao, Dengyue Pan, Mangang Xie, Jizhao Liu

AAAI 2026 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 0 citations (OpenAlex)

Read the paper

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
replace MLP-based Spiking PointNet with DC-CCNNpoint cloud classifier · ModelNet40Overall accuracy (%): 83.5 -> 93.5Improved
use DC-CCNN instead of PointMLP on clean dataDC-CCNN · ScanObjectNNOverall accuracy (%): 85.4 -> 87.3Improved
use DC-CCNN instead of PointMLP on clean ModelNet40DC-CCNN · ModelNet40Overall accuracy (%): 93.2 -> 93.5No clear effect
use DC-CCNN instead of PointMLP under extreme sparsityDC-CCNN · ModelNet40 (128 points)Overall accuracy (%): 37.8 -> 60.3Improved
use DC-CCNN instead of PointMLP under heavy Gaussian noiseDC-CCNN · ModelNet40 (Gaussian noise 0.09)Overall accuracy (%): 79.7 -> 90.8Improved
use DC-CCNN instead of PointMLP under 50% salt-and-pepper noiseDC-CCNN · ModelNet40 (salt-and-pepper 0.5)Overall accuracy (%): 49.2 -> 62.8Improved
use DC-CCNN instead of PointMLP under extreme sparsity on real scansDC-CCNN · ScanObjectNN (128 points)Overall accuracy (%): 39.7 -> 54.8Improved
use DC-CCNN instead of PointMLP on ShapeNetPartDC-CCNN · ShapeNetPartClass mIoU (%): 83.9 -> 84.6Improved
add spatial coupling and dynamic threshold to signal accumulation (full model vs signal accumulation only) (ablation)DC-CCNN · ModelNet40 (salt-and-pepper 0.5)Overall accuracy (%): 53.0 -> 62.8Improved
add signal accumulation and dynamic threshold to spatial coupling (full vs spatial coupling only) (ablation)DC-CCNN · ModelNet40 (salt-and-pepper 0.5)Overall accuracy (%): 66.9 -> 62.8Hurt
add spatial coupling and dynamic threshold to signal accumulation (full vs signal accumulation only) (ablation)DC-CCNN · ModelNet40 (128 points)Overall accuracy (%): 60.9 -> 60.3Hurt
add the other two modules to dynamic threshold only (full vs dynamic threshold only) (ablation)DC-CCNN · ModelNet40 (128 points)Overall accuracy (%): 54.3 -> 60.3Improved

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