GMFlow: Global Motion-Guided Recurrent Flow for 6D Object Pose Estimation
This addresses occlusion challenges in 6D pose estimation for robotic perception and manipulation, representing an incremental improvement over existing refinement methods.
The paper tackles the problem of 6D object pose estimation under occlusion and incomplete visibility by proposing GMFlow, a global motion-guided recurrent flow method that leverages structural information to extend motion from visible to invisible regions. Experiments on LM-O and YCB-V datasets show it outperforms existing methods in accuracy while maintaining competitive computational efficiency.
6D object pose estimation is crucial for robotic perception and precise manipulation. Occlusion and incomplete object visibility are common challenges in this task, but existing pose refinement methods often struggle to handle these issues effectively. To tackle this problem, we propose a global motion-guided recurrent flow estimation method called GMFlow for pose estimation. GMFlow overcomes local ambiguities caused by occlusion or missing parts by seeking global explanations. We leverage the object's structural information to extend the motion of visible parts of the rigid body to its invisible regions. Specifically, we capture global contextual information through a linear attention mechanism and guide local motion information to generate global motion estimates. Furthermore, we introduce object shape constraints in the flow iteration process, making flow estimation suitable for pose estimation scenarios. Experiments on the LM-O and YCB-V datasets demonstrate that our method outperforms existing techniques in accuracy while maintaining competitive computational efficiency.