AI Paper Atlas

Research map / Point clouds / Point cloud classification

GenFlow3D: Generative Scene Flow Estimation and Prediction on Point Cloud Sequences

Hanlin Li, Wenming Weng, Yueyi Zhang, Zhiwei Xiong

ICCV 2025 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 0 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 multi-scale diffusion refinement (ablation)GenFlow3D · Argoverse 2Overall EPE3D: 0.1796 -> 0.0646Improved
use transformer-based denoiser instead of setconv (ablation)GenFlow3D · Argoverse 2EPE3D SF1/SF2: 8.3% for SF1 and 7.3% for SF2 lower EPE3DImproved
add hidden state to condition signal (ablation)GenFlow3D · Argoverse 2Overall EPE3D: 0.3337 -> 0.0646Improved
add correlation feature to condition signal (ablation)GenFlow3D · Argoverse 2Overall EPE3D: 0.6008 -> 0.0646Improved
add encoder feature to condition signal (ablation)GenFlow3D · Argoverse 2Overall EPE3D: 0.0805 -> 0.0699Improved
add coarse flow information to condition signal (ablation)GenFlow3D · Argoverse 2Overall EPE3D: 0.0723 -> 0.0699Improved
add temporal initialization from previous full flow (ablation)GenFlow3D · Argoverse 2EPE3D SF3: 11.1% drop on EPE3D for predicting SF3Improved
initialize from deepest-level instead of full previous flow (ablation)GenFlow3D · Argoverse 2Overall EPE3D: 0.0646 -> 0.0689Hurt
use sequence history (SF2 vs SF1)GenFlow3D · nuScenesEPE3D: 0.0162 -> 0.0139 (14.2% lower)Improved
lengthen input sequence from N=2 to N=4 (ablation)GenFlow3D · nuScenesEPE3D SF4: 0.0175 -> 0.0152Improved
increase prediction length from M=1 to M=2 (ablation)GenFlow3D · nuScenes (N=3)EPE3D SF4: 0.0161 -> 0.0172Hurt
use diffusion decoder vs DifFlow3D baselineGenFlow3D · nuScenes SF2EPE3D: 0.0221 -> 0.0139Improved

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