AI Paper Atlas

Research map / Point clouds / Point cloud classification

Boosting 3D Single Object Tracking with 2D Matching Distillation and 3D Pre-training

Qiangqiang Wu, Yan Xia, Jia Wan, Antoni Chan

ECCV 2024 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 14 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 Point-MAE 3D pre-training to SiamBase (ablation)SiamBase · KITTI VanPrecision: 64.3 -> 69.3Improved
add 2D matching distillation to SiamBase with 3D pre-training (ablation)SiamBase · KITTI VanPrecision: 69.3 -> 75.0Improved
add 2D matching distillation to MemBase with 3D pre-training (ablation)MemBase · KITTI VanPrecision: 76.5 -> 79.3Improved
add IoU weighting to matching distillation (ablation)SiamDisst · KITTI VanSuccess/Precision: 56.4/66.3 -> 63.5/75.0Improved
use learnable projection in TAP instead of z-axis values (ablation)SiamDisst · KITTI VanSuccess/Precision: 61.1/72.3 -> 63.5/75.0Improved
add target-aware cross-attention in TAP (ablation)SiamDisst · KITTI VanSuccess/Precision: 61.2/73.1 -> 63.5/75.0Improved
use Point-MAE rather than ReCon, 2D MAE or DropMAE initialization (ablation)SiamDisst · KITTI VanSuccess/Precision: 60.5/69.9 (2D MAE) -> 63.5/75.0Improved
use heavier ViT-384-6 instead of ViT-96-3 matching module (ablation)SiamDisst · KITTI VanSuccess/Precision: 60.5/71.7 -> 63.5/75.0Improved
use heavier ViT-384-6 instead of ViT-96-3 matching module (ablation)MemDisst · KITTI VanSuccess/Precision: 66.6/79.3 vs 66.7/79.1No clear effect
apply matching distillation and 3D pre-training to STNet-style Siamese trackerSiamDisst vs STNet · KITTI (Mean)Success/Precision: 61.3/80.1 -> 66.2/83.9Improved
MemDisst versus MBPTrack on Waymo generalizationMemDisst · Waymo Open Dataset (Mean)Success: 46.0 vs 45.9No clear effect

Earlier methods this paper compares with

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