Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Rethinking Transparent Object Grasping: Depth Completion with Monocular Depth Estimation and Instance Mask
Yaofeng Cheng, Xinkai Gao, Sen Zhang +4
Due to the optical properties, transparent objects often lead depth cameras to generate incomplete or invalid depth data, which in turn reduces the accuracy and reliability of robo…
cs.CV2024
Learning effective pruning at initialization from iterative pruning
Shengkai Liu, Yaofeng Cheng, Fusheng Zha +4
Pruning at initialization (PaI) reduces training costs by removing weights before training, which becomes increasingly crucial with the growing network size. However, current PaI m…