AI Paper Atlas

Research map / Point clouds / Point cloud classification

GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding

Changshuo Wang, Meiqing Wu, Siew-Kei Lam, Xin Ning, Shangshu Yu, Ruiping Wang, Weijun Li, Thambipillai Srikanthan

ECCV 2024 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 36 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
combine ADGConv, RCA and MHA in the Global Perception Module (ablation)GPSFormer GPM · ScanObjectNN PB_T50_RSoverall accuracy: 93.2 (ADGConv only) -> 95.4Improved
add RCA to ADGConv (ablation)GPSFormer GPM · ScanObjectNN PB_T50_RSoverall accuracy: 93.2 -> 94.4Improved
add MHA to ADGConv (ablation)GPSFormer GPM · ScanObjectNN PB_T50_RSoverall accuracy: 93.2 -> 95.0Improved
vary ADGConv neighborhood size, 20 versus 5 or 30 (ablation)ADGConv · ScanObjectNN PB_T50_RSoverall accuracy: 88.6 (k=5), 95.4 (k=20), 93.2 (k=30)Mixed
use learnable polynomial order terms (s=1, p learnable) instead of ABF or RBF (ablation)LSFConv · ScanObjectNN PB_T50_RSaccuracy: 92.8 (ABF) / 93.2 (RBF) -> 95.4Improved
train from scratch rather than pre-trained on few-shot ScanObjectNNGPSFormer · ScanObjectNN few-shot 5-way 10-shotaccuracy: 89.3 -> 71.7Hurt
apply test-time voting (ablation)GPSFormer · ScanObjectNN PB_T50_RSoverall accuracy: 95.0 -> 95.4Improved
use GPSFormer instead of larger supervised modelspoint cloud classifier · ModelNet40overall accuracy: 94.2 vs PointGPT 94.9 and RepSurf-U 94.7No clear effect

Later papers that compared with this method

1 later accepted paper reports GPSFormer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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