AI Paper Atlas

Research map / 3D vision / Depth and stereo

SceneTracker: Long-Term Scene Flow Estimation Network

Bo Wang, Jian Li, Yang Yu, Li Liu, Zhenping Sun, Dewen Hu

TPAMI 2025 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 23 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 depth residual feature (ablation)SceneTracker · LSFOdyssey testdelta_3D^avg: 91.43 -> 95.41Improved
add depth residual feature (ablation)SceneTracker · LSFOdyssey testEPE_3D: 0.085 -> 0.058Improved
update template features during tracking (ablation)SceneTracker · LSFOdyssey testdelta_3D^avg: 95.27 -> 95.41Improved
inference window size 16 instead of 8 (ablation)SceneTracker · LSFOdyssey testdelta_3D^avg: 93.32 -> 95.41Improved
inference window size 24 instead of 16 (ablation)SceneTracker · LSFOdyssey testdelta_3D^avg: 95.41 -> 81.47Hurt
6x2 Transformer blocks instead of 4x2 (ablation)SceneTracker · LSFOdyssey testdelta_3D^avg: 94.93 -> 95.41Improved
8x2 instead of 6x2 Transformer blocks (ablation)SceneTracker · LSFOdyssey testdelta_3D^avg: 95.41 -> 94.10Hurt
add local and global auxiliary pointsSceneTracker ('One' mode) · LSFDriving pedestrianEPE_3D: 2.902 -> 0.707Improved
add global auxiliary points to 'All' inferenceSceneTracker · LSFDriving pedestrianEPE_3D: 2.890 -> 0.486Improved
use SceneTracker instead of SF baselineSceneTracker · LSFOdyssey testMAE_3D: 0.176 -> 0.052Improved
use SceneTracker instead of TAP baselineSceneTracker · LSFOdyssey testEPE_3D: 0.573 -> 0.058Improved
SceneTracker vs SpatialTrackerSceneTracker · LSFDriving backgroundMAE_2D: 1.43 -> 1.85Hurt

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