Problem
Research questions and friction points this paper is trying to address.
Counterfactual world models
response reliability
aggregation weights
LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models
🤖 AI Summary
该研究通过引入LPA-CWM方法，利用Learned Physical Adjudicator学习候选响应的可靠性权重，解决了CWM中不同目标帧掩码响应可靠性差异的问题。
📝 Abstract
Counterfactual world models (CWM) extract motion from pretrained video predictors by comparing factual and intervened predictions. However, responses generated under different target-frame masks vary in reliability, while uniform aggregation weights them equally. We formulate response aggregation as candidate reliability learning and propose LPA-CWM with a lightweight Learned Physical Adjudicator (LPA). Trained on dense MOVi-F trajectories, the 3.0M-parameter LPA compares visual context and response structure across an unordered candidate set to predict relative weights, while the CWM predictor and intervention generator remain frozen. The weighted responses undergo windowed localization and one paired re-evaluation to recover motion. We also introduce Completeness-aware Motion Correspondence (CMC), a ground-truth-anchored evaluation protocol that jointly measures localization, trajectory completeness, visibility, and continuity, counting missing predictions as failures on visible dynamic points. On the evaluated DAVIS and Kinetics subsets, LPA-CWM improves $\mathrm{DCA}_{\mathrm{avg}}$ over Uniform CWM by 60.0\% and 29.0\%, respectively, and also improves tracking accuracy under TAP-Vid First. A quick overview is available at https://LPA-CWM.github.io.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Learned Physical Adjudicator
Counterfactual World Models
Response Reliability Learning
Completeness-aware Motion Correspondence
🔎 Similar Papers
No similar papers found.
