3 papers
cs.CV2026
Seeing the World and the Self from Egocentric Video
Kai Guan, Minchao Jiang, Ruichen WangLi +2
Complete 3D perception from egocentric video requires recovering the surrounding scene and the wearer's full-body motion in a shared metric frame. Existing methods typically addres…
cs.CV2026
Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models
Jiayu Ding, Zhuodong Liu, Lei Zhang +6
As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. However, current models often ov…
math.DG2026
Uniqueness and Stability of Monge--Ampère Potentials in Big Cohomology Classes
Quang-Tuan Dang, Lei Zhang, Bin Zhou
In this paper, we establish a stability estimate and a uniform estimate for the modulus of continuity of solutions to the degenerate complex Monge-Ampère equation in big cohomology…