Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
MultiDiffSense: Diffusion-Based Multi-Modal Visuo-Tactile Image Generation Conditioned on Object Shape and Contact Pose
Sirine Bhouri, Lan Wei, Jian-Qing Zheng +1
Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods ar…
cs.CV2025
SARL: Spatially-Aware Self-Supervised Representation Learning for Visuo-Tactile Perception
Gurmeher Khurana, Lan Wei, Dandan Zhang
Contact-rich robotic manipulation requires representations that encode local geometry. Vision provides global context but lacks direct measurements of properties such as texture an…
cs.CV2025
Physics-Informed Machine Learning for Efficient Sim-to-Real Data Augmentation in Micro-Object Pose Estimation
Zongcai Tan, Lan Wei, Dandan Zhang
Precise pose estimation of optical microrobots is essential for enabling high-precision object tracking and autonomous biological studies. However, current methods rely heavily on…