AI Paper Atlas

Research map / 3D vision / Depth and stereo

Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction

Weirong Chen, Ganlin Zhang, Felix Wimbauer, Rui Wang, Nikita Araslanov, Andrea Vedaldi, Daniel Cremers

ICCV 2025 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 12 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 motion decoupling with the dynamic tracker (ablation)BA-Track · MPI SintelATE: 0.137 -> 0.065Improved
add camera mask (zero weight on dynamic points) to decoupled tracker (ablation)BA-Track · MPI SintelATE: 0.065 -> 0.034Improved
add camera mask to total-motion tracker (ablation)BA-Track · MPI SintelATE: 0.137 -> 0.047Improved
use dual-network decoupling instead of single static-motion tracker (ablation)BA-Track · MPI SintelATE: 0.072 -> 0.034Improved
use decoupling without mask instead of static-only tracker without mask (ablation)BA-Track · MPI SintelATE: 0.091 -> 0.065Improved
add depth consistency loss to refinement (ablation)BA-Track · Bonn crowd2Abs Rel: 0.121 -> 0.103Improved
add scene rigidity loss alone to refinement (ablation)BA-Track · Bonn crowd2Abs Rel: 0.121 -> 0.117Improved
add both depth and rigidity losses (ablation)BA-Track · Bonn crowd2Abs Rel: 0.121 -> 0.089Improved
add depth consistency loss accuracy (ablation)BA-Track · Bonn crowd2delta<1.25 (%): 89.6 -> 95.0Improved
add rigidity loss alone, accuracy (ablation)BA-Track · Bonn crowd2delta<1.25 (%): 89.6 -> 88.4Hurt
apply BA-Track refinement to ZoeDepth (ablation)ZoeDepth · MPI SintelAbs Rel: 0.467 -> 0.408Improved
apply BA-Track refinement to ZoeDepth (ablation)ZoeDepth · AirDOS ShibuyaAbs Rel: 0.571 -> 0.299Improved

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