AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointINet: Point Cloud Frame Interpolation Network

Fan Lu, Guang Chen, Sanqing Qu, Zhijun Li, Yinlong Liu, Alois Knoll

AAAI 2021 · Point clouds › Point cloud classification · approach: LiDAR point cloud compression and completion · 33 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 PointINet instead of Scene flowPoint Cloud Frame Interpolation · KITTI odometryCD: 0.687 -> 0.457Improved
use PointINet instead of Scene flowPoint Cloud Frame Interpolation · KITTI odometryEMD: 57.13 -> 39.46Improved
use PointINet instead of Scene flowPoint Cloud Frame Interpolation · nuScenesCD: 0.511 -> 0.487Improved
use PointINet instead of Scene flowPoint Cloud Frame Interpolation · nuScenesEMD: 50.97 -> 47.98Improved
add adaptive sampling based on target time step (ablation)PointINet · KITTI odometryCD: 0.580 -> 0.457Improved
add adaptive sampling based on target time step (ablation)PointINet · KITTI odometryEMD: 48.00 -> 39.46Improved
add time-step-adaptive neighbor allocation in kNN clusters (ablation)PointINet · KITTI odometryCD: 0.534 -> 0.457Improved
add time-step-adaptive neighbor allocation in kNN clusters (ablation)PointINet · KITTI odometryEMD: 41.66 -> 39.46Improved
add attentive points fusion (ablation)PointINet · KITTI odometryCD: 0.555 -> 0.457Improved
add attentive points fusion (ablation)PointINet · KITTI odometryEMD: 40.67 -> 39.46Improved
interpolate the downsampled stream with PointINetKITTI odometry point-cloud stream · KITTI odometryHarris-3D repeatability: 0.155 -> 0.138Hurt
interpolate the downsampled stream with PointINetKITTI odometry point-cloud stream · KITTI odometrySIFT-3D repeatability: 0.174 -> 0.151Hurt

Later papers that compared with this method

4 later accepted papers report PointINet as a baseline in their results tables; 4 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