AI Paper Atlas

Research map / Point clouds / Point cloud classification

RMS-FlowNet++: Efficient and Robust Multi-scale Scene Flow Estimation for Large-Scale Point Clouds

Ramy Battrawy, René Schuster, Didier Stricker

IJCV 2024 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 14 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
reduce correspondence set Kp from 33 to 16 (ablation)RMS-FlowNet · FT3Ds / KITTIsAcc3DR: 95.60 -> 95.15 (FT3Ds); 95.80 -> 91.72 (KITTIs)Hurt
add graph representation to flow embedding (ablation)RMS-FlowNet++ (FPS) · FT3DsAcc3DR: 95.15 -> 96.85Improved
omit the decoder in feature extraction (ablation)RMS-FlowNet++ (FPS) · FT3DsAcc3DR: 96.85 -> 97.63Improved
add 2nd embedding step in feature space (ablation)RMS-FlowNet++ (FPS) · KITTIsAcc3DR: 94.57 -> 95.52Improved
add bidirectional similarity map (ablation)RMS-FlowNet++ (FPS) · FT3DsAcc3DR: 97.77 -> 98.09Improved
add bidirectional similarity map (ablation)RMS-FlowNet++ (FPS) · KITTIsAcc3DR: 95.52 -> 97.63Improved
add spatial encoding to stacked attention (ablation)RMS-FlowNet++ (FPS) · FT3DsAcc3DR: 95.13 -> 96.84Improved
add reference-frame feature f_i^t to attention input (ablation)RMS-FlowNet++ (FPS) · FT3DsAcc3DR: 96.84 -> 97.20Improved
add residual connection to stacked attention (ablation)RMS-FlowNet++ (FPS) · FT3DsAcc3DR: 97.20 -> 98.09Improved
increase Kp from 8 to 16 (FPS) (ablation)RMS-FlowNet++ · FT3DsAcc3DR: 97.70 -> 98.09Improved
increase Kp from 16 to 20 (FPS) (ablation)RMS-FlowNet++ · FT3DsAcc3DR: 98.09 -> 98.07No clear effect
train with random sampling (Kp=20) instead of FPS (Kp=16) (ablation)RMS-FlowNet++ · KITTIsAcc3DR: 97.63 -> 97.67Improved

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