AI Paper Atlas

Research map / 3D vision / Depth and stereo

SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion

Yuxi Xiao, Jianyuan Wang, Nan Xue, Nikita Karaev, Yuri Makarov, Bingyi Kang, Xing Zhu, Hujun Bao, Yujun Shen, Xiaowei Zhou

ICCV 2025 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 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 camera pose estimation (offl+ vs offl-) (ablation)SpatialTrackerV2 + MegaSAM · TAPVid-3D Aria subsetAJ (3D): 22.3 -> 24.7Improved
add camera pose estimation (offl+ vs offl-) (ablation)SpatialTrackerV2 + MegaSAM · TAPVid-3D Aria subsetAPD3D: 32.2 -> 35.2Improved
add camera pose estimation (offl+ vs offl-) (ablation)SpatialTrackerV2 + MegaSAM · TAPVid-3D averageAJ (3D): 18.7 -> 19.8Improved
use MegaSAM instead of UniDepthV2 depthCoTracker3 · TAPVid-3D averageAJ (3D): 12.8 -> 17.3Improved
replace SyncFormer with simple 3D projection layer (ablation)CoTracker3 · TAP-Vid DAVISAJ: 64.4 -> 51.6Hurt
replace SyncFormer with simple 3D projection layer (ablation)CoTracker3 · TAP-Vid DAVISOA: 91.2 -> 85.3Hurt
add VKITTI and PointOdyssey with joint training (ablation)Base tracker · TAPVid-3D DriveTrackAJ (3D): 7.4 -> 14.7Improved
add VKITTI and PointOdyssey with joint training (ablation)Base tracker · TAPVid-3D DriveTrackAPD3D: 13.3 -> 21.9Improved
add VKITTI and PointOdyssey with joint training (ablation)Base tracker · TAPVid-3D Aria subsetAJ (3D): 16.0 -> 15.7No clear effect
add VKITTI and PointOdyssey with joint training (ablation)Base tracker · TAPVid-3D PStudioAJ (3D): 12.6 -> 17.2Improved
add back-end joint motion optimization to front-end (ablation)SpatialTrackerV2 · Camera pose SintelATE: 0.075 -> 0.054Improved
add back-end joint motion optimization to front-end (ablation)SpatialTrackerV2 · Camera pose TUM-dynamicATE: 0.038 -> 0.012Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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