2 papers
cs.CV2026
GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry
Xiankang He, Peile Lin, Ying Cui +3
Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion…
cs.CV2025
Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator
Xiankang He, Dongyan Guo, Hongji Li +3
Recent advances in zero-shot monocular depth estimation(MDE) have significantly improved generalization by unifying depth distributions through normalized depth representations and…