Feed-forward 3D reconstruction models enable efficient geometry estimation from sparse images, but their pretrained nature can make them vulnerable to distribution shifts beyond their training data. Identifying these failure modes is important for understanding when such models can be reliably deployed in unconstrained...
Daisy Li, Kyle Gao, Quan-Yun Wu et al.· 0 citations
Modern image models provide strong cues about \emph{what} should be segmented in each view, but their masks do not by themselves determine \emph{where} those labels should persist in 3D. We present Cross-Domain Segmentation via Gaussian Splatting (CDSeg), a label-transfer interface that requires no task-specific 3D seg...
Wen-Tao Sun, Yi-Ping Chen, Zheng-Sen Xu et al.· 0 citations
Methods that transfer predictions from two-dimensional foundation models into three-dimensional segmentation are commonly grouped by task or representation. Those groupings obscure the decisions that determine whether a system remains coherent across views: where image evidence is grounded, when observations become one...
Wen-Tao Sun, Yi-Ping Chen, J. Zelek et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.