AI Paper Atlas

Research map / Point clouds / Point cloud classification

GSOT3D: Towards Generic 3D Single Object Tracking in the Wild

Yifan Jiao, Yunhao Li, Junhua Ding, Qing Yang, Song Fu, Heng Fan, Libo Zhang

ICCV 2025 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 1 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 9DoF box prediction instead of 7DoF (ablation)PROT3D · GSOT3D testmAO (%): 19.86 -> 20.03Improved
add 9DoF box prediction instead of 7DoF (ablation)PROT3D · GSOT3D testmSR75 (%): 2.36 -> 3.29Improved
add 9DoF box prediction instead of 7DoF (ablation)PROT3D · GSOT3D testmSR50 (%): 15.16 -> 15.46Improved
add progressive architecture (two stages) (ablation)PROT3D · GSOT3D testmAO (%): 20.03 -> 21.97Improved
add progressive architecture (two stages) (ablation)PROT3D · GSOT3D testmSR50 (%): 15.46 -> 19.76Improved
add progressive architecture (two stages) (ablation)PROT3D · GSOT3D testmSR75 (%): 3.29 -> 5.22Improved
use 3 stages instead of 2 (ablation)PROT3D · GSOT3D testmAO (%): 21.97 -> 21.58Hurt
use 3 stages instead of 2 (ablation)PROT3D · GSOT3D testmSR50 (%): 19.76 -> 19.61Hurt
use memory size K=2 instead of 3 (ablation)PROT3D · GSOT3D testmAO (%): 21.97 -> 21.37Hurt
use memory size K=4 instead of 3 (ablation)PROT3D · GSOT3D testmAO (%): 21.97 -> 21.84Hurt
retrain trackers on GSOT3D training set instead of KITTI-pretrainedMBPTrack · GSOT3D testmAO (%): 3.38 -> 20.54Improved
retrain trackers on GSOT3D training set instead of KITTI-pretrainedM2-Track · GSOT3D testmAO (%): 3.65 -> 20.26Improved

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