AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation

Wenxuan Wu, Zhi Yuan Wang, Zhuwen Li, Wei Liu, Li Fuxin

ECCV 2020 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 200 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
use the proposed learnable cost volume instead of PWC-Net inner product cost volume (ablation)PointPWC-Net · FlyingThings3DEPE3D: 0.0821 -> 0.0588Improved
use the proposed cost volume instead of MLP+Maxpool flow embedding (ablation)PointPWC-Net · FlyingThings3DEPE3D: 0.0741 -> 0.0588Improved
add the warping layer (ablation)PointPWC-Net · FlyingThings3DEPE3D: 0.0984 -> 0.0588Improved
add smoothness constraint to Chamfer loss (self-supervised) (ablation)PointPWC-Net · FlyingThings3DEPE3D: 0.2112 -> 0.1304Improved
add Laplacian regularization to Chamfer + smoothness (ablation)PointPWC-Net · FlyingThings3DEPE3D: 0.1304 -> 0.1213Improved
self-supervised fine-tuning on KITTI after self-supervised pretraining (Self+Self)PointPWC-Net · KITTIEPE3D: 0.2549 -> 0.0461Improved
self-supervised fine-tuning on KITTI after full supervision (Full+Self)PointPWC-Net · KITTIEPE3D: 0.0694 -> 0.0430Improved
PointPWC-Net versus HPLFlowNet (fully supervised)PointPWC-Net · FlyingThings3DEPE3D: 0.0804 -> 0.0588Improved
PointPWC-Net versus HPLFlowNet on KITTI without fine-tuningPointPWC-Net · KITTIEPE3D: 0.1169 -> 0.0694Improved
self-supervised PointPWC-Net versus CPD(non-rigid) on KITTIPointPWC-Net · KITTIEPE3D: 0.4144 -> 0.2549Improved
supervised training (Full) versus self-supervised trainingPointPWC-Net · FlyingThings3DEPE3D: 0.1213 -> 0.0588Improved
PointPWC-Net runtime versus HPLFlowNetPointPWC-Net · FlyingThings3Druntime (ms): 98.4 -> 117.4No clear effect

Later papers that compared with this method

11 later accepted papers report PointPWC-Net as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.

3 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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