AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification

Hao Yang, Qianyu Zhou, Haijia Sun, Xiangtai Li, Xuequan Lu, Lizhuang Ma, Shuicheng YAN

AAAI 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 1 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 AGT-Shift to V-RWKV baseline (ablation)V-RWKV · PointDA-10avg accuracy: 72.24 -> 73.57Improved
add CD-KDA to V-RWKV baseline (ablation)V-RWKV · PointDA-10avg accuracy: 72.24 -> 74.28Improved
combine AGT-Shift and CD-KDA (ablation)V-RWKV · PointDA-10avg accuracy: 72.24 -> 75.66Improved
use AGT-Shift instead of KNN-based token shifts (ablation)PointDGRWKV · PointDA-10avg accuracy: 74.82 -> 75.66Improved
align only keys rather than values in CD-KDA (ablation)CD-KDA · PointDA-10avg accuracy: 74.08 -> 75.66Improved
also align values in addition to keys (ablation)CD-KDA · PointDA-10avg accuracy: 75.66 -> 75.68No clear effect
scale up network (larger dim, denser sampling) (ablation)PointDGRWKV · PointDA-10avg accuracy: 75.66 -> 76.13Improved
halve number of blocks (ablation)PointDGRWKV · PointDA-10avg accuracy: 75.66 -> 75.15Hurt
PointDGRWKV vs PointDGMambaPointDG-3to1 · PointDG-3to1avg accuracy: 80.53 -> 81.92Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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