Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
Runsong Zhu, Jiaxin Guo, Xiaoyang Guo +9
This paper introduces EPS3D, a new end-to-end feed-forward framework for open-vocabulary 3D panoptic segmentation. Unlike existing methods relying on additional preprocessing, we d…
cs.CV2026
Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning
Yiyao Ma, Kai Chen, Zhongxiang Zhou +5
Monocular 3D shape recovery is fundamental to geometric understanding, yet achieving robust generalization across arbitrary viewpoints and unseen object categories remains a signif…
cs.CV2026
RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
Jianing Guo, Zhenhong Wu, Chang Tu +13
In Vision-Language-Actionf(VLA) models, robustness to real-world perturbations is critical for deployment. Existing methods target simple visual disturbances, overlooking the broad…