AI Paper Atlas

Research map / Point clouds / Point cloud classification

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences

Xingyu Liu, Mengyuan Yan, Jeannette Bohg

ICCV 2019 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 236 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 more input frames to MeteorNet-cls (4 -> 24) (ablation)MeteorNet-cls · MSRAction3Daccuracy: 78.11 -> 88.50Improved
use a multi-frame point cloud sequence (24 frames) instead of a single framePointNet++ · MSRAction3Daccuracy: 61.61 -> 88.50Improved
increase frames from 16 to 24 for action recognition (ablation)MeteorNet-cls · MSRAction3Daccuracy: 88.21 -> 88.50No clear effect
add multiple frames to a single-frame point networkPointNet++ · Synthia (segmentation)mIoU: 79.35 -> 81.80Improved
enlarge the max-pooling bottleneck dimension (seg-s to seg-m) (ablation)MeteorNet-seg · Synthia (segmentation)mIoU: 80.31 -> 81.72Improved
enlarge non-bottleneck layer widths (seg-m to seg-l) with 3 frames (ablation)MeteorNet-seg · Synthia (segmentation)mIoU: 81.13 -> 81.80Improved
increase input frames from 2 to 3 without enlarging the model (ablation)MeteorNet-seg-m · Synthia (segmentation)mIoU: 81.72 -> 81.13Hurt
use point-based MeteorNet instead of sparse-convolution MinkNet4D MinkNet14 · Synthia (segmentation)mIoU: 77.46 -> 81.80Improved
add a third input frame (ablation)MeteorNet-seg · KITTI (segmentation)mIoU: 71.65 -> 73.42Improved
add a third frame for the Car class (ablation)MeteorNet-seg · KITTI (segmentation, Car IoU)IoU: 74.53 -> 71.22Hurt
add a fourth frame for scene flow (chained-flow) (ablation)MeteorNet-flow · FlyingThings3D (scene flow)mean EPE: 0.215 -> 0.209Improved
use chained-flow grouping instead of direct grouping (4 frames) (ablation)MeteorNet-flow · FlyingThings3D (scene flow)accuracy (EPE<0.1): 52.12 -> 49.91Hurt

Later papers that compared with this method

5 later accepted papers report Meteornet as a baseline in their results tables; 5 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