14 papers
GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation
Yonglong Zhang, Zongwu Xie, Yang Liu
Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometr…
HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation
Guanghu Xie, Mingxu Li, Shuo Zhang +5
Flow policies can represent multimodal action distributions for robot manipulation, yet a robot must execute one action at each control step. When several proposals are sampled, cr…
GAP-GDRNet: Geometry-aware monocular 6D pose estimation for spacecraft using synthetic geometric supervision
Zongwu Xie, Yonglong Zhang, Yifan Yang +2
Monocular spacecraft 6D pose estimation remains difficult under weak texture, thin structures, illumination variation, and occlusion. This article presents GAP-GDRNet, a geometry-a…
Precision-Aware Illumination-Disentangled Vision Transformer for Spacecraft 6D Pose Estimation
Zongwu Xie, Yifan Yang, Yonglong Zhang +3
Vision sensors provide a lightweight solution for spacecraft proximity operations, but monocular spacecraft 6D pose estimation remains difficult under illumination variation, specu…
Component-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data Construction
Zongwu Xie, Yonglong Zhang, Yifan Yang +3
For camera-based satellite visual sensing, Sim2Real data construction requires images that approach real-domain sensor appearance while retaining the annotations inherited from sim…
Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
Wandong Sun, Yongbo Su, Leoric Huang +10
Achieving robust vision-based humanoid locomotion remains challenging due to two fundamental issues: the sim-to-real gap introduces significant perception noise that degrades perfo…