Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation
Lu Zhang,Siqi Zhang,Xu Yang,Hong Qiao,Zhiyong Liu,Lu Zhang,Siqi Zhang,Xu Yang,Hong Qiao,Zhiyong Liu
Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the model to unseen real-world scenarios. However, the domain shift caused by the sim2real gap is inevitable, posing a crucial challenge to the segmentation model. In ...
