3 papers
cs.CV2026
SurgCast: Action-Conditioned Future Skeletons for Controllable Surgical World Models
Wanhao Liu, Rulin Zhou, Liangjing Shao +9
Surgical world models must turn prospective robot actions into visually faithful, structurally consistent instrument motion. We introduce SurgCast, which predicts future instrument…
cs.CV2026
NCGR: Noise-Conditional Gated Rectification for Camera Extrinsic Perturbations in BEV 3D Object Detection
Wenbin Pan, Wanhao Liu, Liwei Luo +3
Camera-based bird's-eye-view (BEV) 3D detection typically assumes accurate and fixed camera extrinsics. In detectors using spatial cross-attention (SCA), extrinsic perturbations di…
cs.CV2026
CrossScope: A Role-Asymmetric World Model for Joint Dual-Scope Surgical Video Prediction
Wanhao Liu, Jinsong Lin, Rulin Zhou +11
Visual world models typically learn future dynamics from a single observation stream, limiting their ability to model cooperative systems with multiple independently moving observe…