AI Paper Atlas

Research map / Point clouds / Point cloud classification

Efficient Spiking Point Mamba for Point Cloud Analysis

Peixi Wu, Bosong Chai, Menghua Zheng, Wei Li, Zhangchi Hu, Jie Chen, Zheyu Zhang, Hebei Li, Xiaoyan Sun

ICCV 2025 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 9 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
add SNN-adapted Gate II and bidirectional SSM (SMB) over vanilla Mamba block (ablation)SPM · ScanObjectNN OBJ-BGoverall accuracy: 88.3 -> 90.2Improved
add SNN-adapted Gate II and bidirectional SSM (SMB) over vanilla Mamba block (ablation)SPM · ModelNet40overall accuracy: 91.4 -> 92.3Improved
add bidirectional SSM branch (Gate I) (ablation)SPM Model I · ScanObjectNN PB-T50-RSoverall accuracy: 83.1 -> 83.8Improved
add SNN-adapted Gate II (ablation)SPM Model I · ScanObjectNN PB-T50-RSoverall accuracy: 83.1 -> 83.5Improved
flip time dimension instead of no flip in SSM branch (ablation)SPM · ScanObjectNN OBJ-BGoverall accuracy: 88.9 -> 90.2Improved
add Token Flip rather than Time Flip (ablation)SPM · ScanObjectNN OBJ-BGoverall accuracy: 90.2 -> 89.6Hurt
apply both Token Flip and Time Flip (ablation)SPM · ScanObjectNN OBJ-BGoverall accuracy: 90.2 -> 89.2Hurt
add HDE finite forward sliding and infinite backward extension (ablation)SPM · ScanObjectNN OBJ-BGoverall accuracy: 88.6 -> 90.2Improved
add HDE finite forward sliding and infinite backward extension (ablation)SPM · ModelNet40overall accuracy: 91.5 -> 92.3Improved
increase time step from 1 to 4 (ablation)SPM · ScanObjectNN PB-T50-RSoverall accuracy: 83.3 -> 84.2Improved
increase time step from 4 to 6 (ablation)SPM · ScanObjectNN PB-T50-RSoverall accuracy: 84.2 -> 84.3No clear effect
replace LIF neuron with ILIF neuron (ablation)SPM · ScanObjectNN OBJ-BGoverall accuracy: 90.2 -> 91.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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