AI Paper Atlas

Research map / Point clouds / Point cloud classification

Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding

Hao Wen, Yunze Liu, Jingwei Huang, Bo Duan, Li Yi

ECCV 2022 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 40 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 hierarchical PPTr (1 frame) instead of P4Transformer (3 frames)P4Transformer · Synthia 4DmIoU: 83.16 -> 83.85Improved
add 30-frame primitive memory pool instead of 1 framePPTr · Synthia 4DmIoU: 83.85 -> 84.49Improved
add 30-frame primitive memory pool instead of 3 framesPPTr · HOI4DmIoU: 68.54 -> 70.13Improved
replace P4Transformer with PPTr (1 frame)P4Transformer · HOI4DmIoU: 59.61 -> 68.07Improved
replace P4Transformer with PPTr (24 frames)P4Transformer · MSR-Action3Daccuracy: 90.94 -> 92.33Improved
add intra-primitive transformer (ablation)PPTr · MSR-Action3Daccuracy: 16.73 accuracy drop without itImproved
add inter-primitive (primitive) transformer (ablation)PPTr · MSR-Action3Daccuracy: 1.39 accuracy drop without itImproved
use primitive planes instead of K-means clusters as mid-level representation (ablation)PPTr · Synthia 4DmIoU: 80.70 -> 84.49Improved
use primitive planes instead of BPSS supervoxels (ablation)PPTr · Synthia 4DmIoU: 83.43 -> 84.49Improved
use primitive planes instead of BPSS supervoxels (ablation)PPTr · MSR-Action3Daccuracy: 91.98 -> 92.33Improved
vary primitive number from 100 to 400 (ablation)PPTr · Synthia 4DmIoU: 84.41, 84.49, 84.28No clear effect
use 10 primitives instead of 200 (ablation)PPTr · Synthia 4DmIoU: 84.49 -> 82.98Hurt

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