AI Paper Atlas

Research map / Point clouds / Point cloud classification

Self-Supervised 3D Scene Flow Estimation and Motion Prediction Using Local Rigidity Prior

Ruibo Li, Chi Zhang, Zhe Wang, Chunhua Shen, Guosheng Lin

TPAMI 2024 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 6 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 region-wise rigid alignment instead of nearest-neighbor matching (ablation)RigidFlow · FT3Ds testEPE: 0.242 -> 0.059Improved
add region-wise rigid alignment instead of nearest-neighbor matching (ablation)RigidFlow · FT3Do testEPE: 0.734 -> 0.210Improved
use full rigid alignment instead of only center alignment (ablation)RigidFlow · FT3Ds testEPE: 0.100 -> 0.059Improved
use full rigid alignment instead of only center alignment (ablation)RigidFlow · FT3Do testEPE: 0.225 -> 0.210Improved
add confidence reweighting from forward-backward consistency (ablation)RigidFlow · FT3Do testEPE: 0.210 -> 0.173Improved
add validity reasoning for pseudo labels (ablation)RigidFlow · FT3Ds testEPE: 0.059 -> 0.051Improved
add validity reasoning for pseudo labels (ablation)RigidFlow · FT3Do testEPE: 0.210 -> 0.167Improved
add both confidence reweighting and validity reasoning (RigidFlow++) (ablation)RigidFlow · FT3Ds testEPE: 0.059 -> 0.047Improved
add both confidence reweighting and validity reasoning (RigidFlow++) (ablation)RigidFlow · FT3Do testEPE: 0.210 -> 0.144Improved
increase update iterations from 1 to 4 (ablation)RigidFlow++ · FT3Ds testEPE: 0.052 -> 0.047Improved
increase update iterations from 1 to 4 (ablation)RigidFlow++ · FT3Do testEPE: 0.152 -> 0.144Improved
increase supervoxel number from 10 to 30 (ablation)RigidFlow++ · FT3Ds testEPE: 0.057 -> 0.047Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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