AI Paper Atlas

Research map / Point clouds / Point cloud classification

FlowCloud: Learning Continuous Spatiotemporal Dynamics from Unpaired Sparse Point Cloud Snapshots

Yinbo Liu, Keyang Ye, Wenshan Sun, Handi Gao, Tian Tian

ICML 2026 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds

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 Neural ODE continuous dynamics (vs discrete dynamics) (ablation)FlowCloud · Simulation 2D extrapolationChamfer distance: 0.5517 -> 0.0449Improved
add Point Swin Transformer encoder (vs PointNet++) (ablation)FlowCloud · Simulation 2Dcell type accuracy: 0.812 -> 0.898Improved
add global sequence context (vs recursive aggregation) (ablation)FlowCloud · Simulation 2D extrapolationChamfer distance: 0.3105 -> 0.0449Improved
add global sequence context (vs recursive aggregation) (ablation)FlowCloud · Simulation 2Dcell type accuracy: 0.763 -> 0.898Improved
add trajectory consistency loss (ablation)FlowCloud · Simulation 2D extrapolationChamfer distance: 0.0691 -> 0.0449Improved
add Transformer attention aggregator (vs mean pooling) (ablation)FlowCloud · Simulation 2D extrapolationChamfer distance: 0.0840 -> 0.0449Improved
FlowCloud vs best baseline SPCMNet on human motionFlowCloud · Human 3D interpolationChamfer distance: 0.0470 -> 0.0268Improved
FlowCloud vs OT baseline Moscot on Drosophila cell typesFlowCloud · Drosophila 3Dcell type accuracy: 0.0442 -> 0.1086Improved
FlowCloud vs SPCMNet on Ambystoma geometryFlowCloud · Ambystoma 2DSinkhorn distance: Meteornet 0.2881 vs FlowCloud 0.2868Mixed
FlowCloud vs Meteornet on Drosophila SinkhornFlowCloud · Drosophila 3DSinkhorn distance: 0.2021 -> 0.2238Hurt
FlowCloud vs SPCMNet on simulation extrapolation cell type accuracyFlowCloud · Simulation 2D extrapolationcell type accuracy: 0.4056 -> 0.4581Improved

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