AI Paper Atlas

Research map / 3D vision / Human pose estimation

HumanBA: Human-Aware Bundle Adjustment via Global Human-Camera Decoupling

Fengyuan Yang, Tanuj Sur, Tze Ho Elden Tse, Angela Yao

CVPR 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture

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 human joints as pseudo-static BA landmarks on top of masked DROID with scale estimation (ablation)Masked DROID-SLAM · EMDB2W-MPJPE (mm): 230.97 -> 195.97Improved
add human joints as BA landmarks (ablation)Masked DROID-SLAM · EMDB2ATE (m): 0.369 -> 0.358Improved
add human motion refinement (jump filtering and smoothing) (ablation)HumanBA · EMDB2ATE (m): 0.404 -> 0.358Improved
use all joints with equal weight instead of adaptive weighting (ablation)HumanBA · EMDB2ATE (m): 0.508 vs 0.358 (full)Hurt
use only the root joint as target instead of adaptive weighting (ablation)HumanBA · EMDB2ATE-S (m): 0.718 vs 0.682 (full)Hurt
add acceleration-based adaptive target weighting (ablation)HumanBA · EMDB2WA-MPJPE (mm): 74.81 -> 70.10Improved
use no dynamic mask in DROID-SLAM (ablation)DROID-SLAM · EMDB2ATE-S (m): 7.25 -> 7.957 (vs masked)Hurt
evaluate HumanBA on motion-spike sequences onlyHumanBA vs masked DROID + scale est. · EMDB2 (motion-spike sequences)ATE-S (m): 0.649 -> 0.525Improved
replace TRAM with HumanBA on long sequencescamera scale-aware error · EMDB2 (long sequences)ATE-S (m): 0.81 -> 0.90Hurt
replace masked DROID with HumanBAcamera ATE · EMDB2 (all sequences)ATE (m): 0.34 -> 0.32No clear effect
replace TRAM with HumanBAlocal pose · EMDB2PA-MPJPE (mm): 38.6 -> 38.6No clear effect
replace TRAM with HumanBAglobal human · SLOPER4D (3-sequence subset)ATE-S (m): 4.05 -> 3.10Improved

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