SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.01730 · CVPR · 2022

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

Shuguang Cui, Zhen Li, Kong, Haiming Zhang, Chaoda Zheng, Xu Yan, Baoyuan Wang, Shenghui Cheng

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and incomplete, which hinders effective appearance matching. Besides, previous methods greatly overlook the critical motion clues among targets. In this work, beyond 3D Siamese tracking, we introduce a motion-centric paradigm to handle 3D SOT from a new perspective. Following this paradigm, we propose a matching-free two-stage tracker M 2 -Track. At the 1 st -stage, M 2 -Track localizes the target within successive frames via motion transformation. Then it refines the target box through motion-assisted shape completion at the 2 nd -stage. Extensive experiments confirm that M 2 -Track significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS (∼ 8%, ∼ 17% and ∼ 22% precision gains on KITTI, NuScenes, and Waymo Open Dataset respectively). Further analysis verifies each component's effectiveness and shows the motioncentric paradigm's promising potential when combined with appearance matching. Code will be made available at https://github.com/Ghostish/Open3DSOT.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.01730")
get_code_for_paper("2203.01730")
have("2203.01730")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.01730.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.01730.svg)](https://syntology.ai/paper/2203.01730)

Connect an agent — have() is free.