AI Paper Atlas

Research map / Point clouds / Point cloud classification

PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds

Yi Wei, Ziyi Wang, Yongming Rao, Jiwen Lu, Jie Zhou

CVPR 2021 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 95 citations (OpenAlex)

Check 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
combine point-based and voxel-based correlations (ablation)PV-RAFT · FlyingThings3DEPE (m): 0.0741 -> 0.0534 (point-only); 0.0712 -> 0.0534 (voxel-only)Improved
add the refinement module (ablation)PV-RAFT with point-voxel correlation · FlyingThings3DEPE (m): 0.0534 -> 0.0461Improved
increase point KNN neighbors from 32 to 64 or 128 (ablation)PV-RAFT point-correlation-only variant · FlyingThings3DEPE (m): 0.0741 -> 0.2307; 0.0741 -> 0.6076Hurt
use a KNN pyramid with K=16,32,64 or K=32,64,128 (ablation)PV-RAFT point-correlation variant · FlyingThings3DEPE (m): 0.1616; 0.4841Hurt
vary voxel pyramid side length and depth (ablation)PV-RAFT voxel-correlation variant · FlyingThings3DEPE (m): 0.1408; 0.0902; 0.0712; 0.0672Mixed
use both point-voxel correlations instead of voxel correlation alone (ablation)PV-RAFT without refinement · FlyingThings3DEPE (m): 0.0712 -> 0.0534Improved
reduce truncation number to M=128 from M=512 (ablation)PV-RAFT · FlyingThings3DEPE (m): 0.0461 -> 0.0585Hurt
increase truncation number to M=1024 from M=512 (ablation)PV-RAFT · FlyingThings3DEPE (m): 0.0461 -> 0.0475No clear effect
replace point-voxel correlation with MLP+Maxpool correlation (ablation)PV-RAFT correlation module · FlyingThings3DEPE (m): 0.0461 -> 0.0704Hurt
replace point-voxel correlation with patch-to-patch correlation (ablation)PV-RAFT correlation module · FlyingThings3DEPE (m): 0.0461 -> 0.0614Hurt
use PV-RAFT instead of FLOTscene flow estimation · FlyingThings3DEPE (m): 0.052 -> 0.0461Improved
use PV-RAFT instead of FLOTscene flow estimation · KITTIAcc Strict: 0.755 -> 0.8226Improved

Later papers that compared with this method

6 later accepted papers report PV-RAFT as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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