TFENet: Topological Feature Extraction Network for 6D Object Pose Estimation

Grasping is an essential and challenging skill for robots to interact with their environment. Accurately obtaining the 6D pose information of the grasped object is the key to successful grasping. Due to the influence of illumination changes and object textures, the previous methods had problems with low utilization of depth information and inaccurate feature information. We study feature information extraction and fusion to address these issues and proposed a topological feature extraction network (TFENet). Firstly, we design TFE module to achieve global feature extraction from object point clouds, through which features can be identified to use depth information efficiently. Secondly, we design a MFF module to fuse color and geometric embedding better. Finally, experiments show that the proposed method outperforms existing methods with two datasets, LineMOD and YCB-Video.