AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointChain: Learning Generalizable Point Cloud Representations via Structural Chain Modeling

Luyao Wang, Chuxin Wang, Qiao Li, Tianzhu Zhang

AAAI 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 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
use PointNet++-like token embedding (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 90.11 -> 90.53Improved
add structural chain and next-scale prediction pretraining (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 90.53 -> 92.96Improved
add cross-scale semantic alignment contrastive task (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 92.96 -> 93.75Improved
add multi-scale token embedding (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 92.26 -> 92.75Improved
add scale identifier (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 92.75 -> 93.34Improved
add dynamic scaling strategy (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 93.34 -> 93.75Improved
use next-scale prediction instead of masked point modeling (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 92.09 -> 92.96Improved
set fine-tuning regularization weight lambda to 2 instead of 0 (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 91.74 -> 93.75Improved
set lambda to 2 instead of 4 (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 93.44 -> 93.75Improved
use representative points [1 32 128] instead of [1 16 64] (ablation)PointChain (Mamba) · ScanObjectNN OBJ-BGaccuracy (%): 94.84 -> 95.70Improved
use representative points [1 64 256] instead of [1 16 64] (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 93.75 -> 93.03Hurt
swap Transformer for Mamba backbone (ablation)PointChain (Mamba) · ScanObjectNN PB-T50-RSaccuracy (%): 91.50 -> 93.75Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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