AI Paper Atlas

Research map / Point clouds / Point cloud classification

Learning Scene Dynamics from Point Cloud Sequences

Pan Li He, Patrick Emami, Sanjay Ranka, Anand Rangarajan

IJCV 2022 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 24 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
retrain pair-wise model on multi-step SFT3D sequences instead of pair-wise FT3D (ablation)PointPWC-Net · SFT3D validation (SSFE)EPE3D: 0.190 -> 0.115Improved
retrain pair-wise model on SFT3D sequences instead of FT3D (ablation)FlowNet3D · SFT3D validation (SSFE)EPE3D: 0.200 -> 0.136Improved
retrain pair-wise model on SFT3D sequences instead of FT3D (ablation)FLOT · SFT3D validation (SSFE)EPE3D: 0.173 -> 0.159Improved
add recurrent cost volume over the sequence (SPCM-Net vs PointPWC-Net + SFT3D)PointPWC-Net · SFT3D validation (SSFE)EPE3D: 0.115 -> 0.108Improved
add recurrent cost volume (SPCM-Net vs best baselines)PointPWC-Net / FlowNet3D · SFT3D test (SSFE)EPE3D / Acc3DS: EPE3D 0.150 (FlowNet3D) vs 0.157; Acc3DS 0.320 -> 0.380Mixed
add recurrent processing (SPCM-Net vs PointPWC-Net)PointPWC-Net · VKS test (SSFE)EPE3D: 0.0458 -> 0.0454Improved
add SSFE pretraining before SPF finetuning (ablation)SPCM-Net · SFT3D test (SPF)ADE: 0.6286 -> 0.3978Improved
add SSFE pretraining before SPF finetuning (ablation)SPCM-Net · SFT3D validation (SPF)ADE: 0.5069 -> 0.2488Improved
replace PointRNN with SPCM-Net for forecastingPointRNN · VKS (SPF)ADE: 0.2856 -> 0.2768No clear effect
replace PointRNN with SPCM-Net for self-supervised forecastingPointRNN · SAG Argoverse (self-supervised SPF)CD: 1.2322 -> 1.3453Mixed
replace PointRNN with SPCM-Net for forecastingPointRNN · nuScenes (SPF)CD: 0.9750 -> 0.6339Improved
add one more preceding frame (3 to 4) (ablation)SPCM-Net · KITTI scene flow (mean EPE)EPE (mean): 0.229 -> 0.194Improved

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