AI Paper Atlas

Research map / Point clouds / Point cloud classification

Dynamic 3D Point Cloud Sequences as 2D Videos

Yiming Zeng, Junhui Hou, Qijian Zhang, Siyu Ren, Wenping Wang

TPAMI 2024 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 25 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
replace point-based spatio-temporal encoder with SPCV 2D-video encoderPST-Transformer · DeformingThings4D action recognitionaccuracy (%): 76.19 -> 90.48Improved
use SPCV representation instead of point grouping for action recognitionPST-Transformer · DeformingThings4D action recognitionforward time (s): 0.010 -> 0.006Improved
use SPCV representation for temporal interpolationIDEA-Net · DHB SwingEMD (x10^3): 7.07 -> 2.74Improved
use SPCV representation for temporal interpolationIDEA-Net · DHB LongdressEMD (x10^3): 5.92 -> 2.16Improved
use SPCV representation for temporal interpolationIDEA-Net · DHBforward time (s): 0.106 -> 0.014Improved
use SPCV representation for temporal interpolationIDEA-Net · DHB LongdressCD (x10^3): 0.88 -> 0.85No clear effect
frame-wise structurization of static clouds versus RegGeoNetRegGeoNet · DancerCD (x10^-4): 0.659 -> 0.034Improved
frame-wise structurization of static clouds versus Flattening-NetFlattening-Net · ChairCD (x10^-4): 2.881 -> 0.086Improved
add sequence-wise structurization (deformation fields) (ablation)SPCV · point cloud sequencestemporal consistencyImproved
add spatial regularization (lambda_s > 0) (ablation)SPCV · point cloud sequencesspatial smoothnessImproved
add normal regularization (lambda_n > 0) (ablation)SPCV · point cloud sequencesspatial smoothness and temporal consistencyImproved
use the paper's default distance instead of EMD (ablation)SPCV · point cloud sequencessmoothness, consistency, fidelityImproved

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