AI Paper Atlas

Research map / Point clouds / Point cloud classification

Paving the Way for Point Cloud Video Representation Learning Using a PDE Model

Zhuoxu Huang, Zhenkun Fan, Jungong Han, Josef Kittler

TPAMI 2026 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 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 MotionPDE regularizerPSTNet · MSRAction-3Daccuracy: 91.20 -> 94.28Improved
add MotionPDE regularizerPST-Transformer · MSRAction-3Daccuracy: 93.73 -> 96.63Improved
add MotionPDE regularizerPSTNet · UTD-MHADaccuracy: 93.49 -> 95.58Improved
add MotionPDE regularizerPPTr · HOI4D action segmentationaccuracy: 77.4 -> 82.42Improved
add MotionPDE regularizerPointLSTM · SHREC 2017 (no BBox)accuracy: 92.50 -> 93.69Improved
add spectral method (trigonometric operators) to the PDE solver (ablation)PSTNet + MotionPDE · MSRAction-3Daccuracy: 92.25 -> 94.28Improved
increase operators from 16 to 32 (ablation)PSTNet + MotionPDE · MSRAction-3Daccuracy: 94.28 -> 91.91Hurt
reduce latent tokens from 4 to 2 (ablation)PSTNet + MotionPDE · MSRAction-3Daccuracy: 94.28 -> 91.58Hurt
add max pooling on the spatial branch (ablation)PSTNet + MotionPDE · MSRAction-3Daccuracy: 94.95 -> 94.28No clear effect
add max pooling on the spatial branch (ablation)PST-Transformer + MotionPDE · MSRAction-3Daccuracy: 95.96 -> 96.63No clear effect
pre-train with MotionPDE contrastive loss then fine-tunePST-Transformer · MSRAction-3Daccuracy: 94.33 -> 97.30Improved
pre-train on NTU60 (sparse stride) then fine-tune on MSRPSTNet · MSRAction-3Daccuracy: 90.57 -> 90.23Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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