GAUGE：面向前馈式 4D 跟踪的组级视角不一致性校正

This paper has been withdrawn by Zhuoqian Feng

No PDF available, click to view other formats

Abstract:Feed-forward models regress dense 3D point trajectories directly from monocular video, yet the residual after global alignment is substantial and lacks a structural explanation. Measured on dynamic query points across models and datasets, the error concentrates along the view direction, while the scale correction each motion group requires differs. The predicted displacement direction nevertheless supports reliable grouping, with a median angle far below the 90° random baseline. The systematic part of the residual is therefore a family of radial degrees of freedom per motion group, along directions 2D observations cannot constrain. We call it group-wise view inconsistency. We present GAUGE (Group-wise Adaptive Unsupervised Gauge Estimation), a training-free and model-agnostic post-hoc module. It recovers motion groups from direction consistency and spatial connectivity, then estimates a per-frame radial scale and group-level translation from 1% to 5% metric anchors, four degrees of freedom per group and frame. On dynamic query points of eight trackers, including D4RT, 4RC and SM4RT, our correction lowers endpoint error by 15.1% to 62.6% over the uncorrected predictions, while spending the same anchors on gradient fine-tuning improves the same models by only -1.1% to 15.2%. Code is publicly available at this https URL.

Comments:	For major updates
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2609.32596 [cs.CV]
	(or arXiv:2609.32596v2 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2609.32596 arXiv-issued DOI via DataCite

Submission history

From: Zhuoqian Feng [view email]
[v1] Sat, 26 Sep 2026 13:14:53 UTC (6,061 KB)
[v2] Tue, 27 Oct 2026 02:27:01 UTC (1 KB) (withdrawn)