PhysPose: Refining 6D Object Poses with Physical Constraints
This addresses the issue of physical plausibility in pose estimation for applications like robotics and augmented reality, representing an incremental improvement by refining existing methods with physical constraints.
The paper tackles the problem of physically inconsistent 6D object pose estimates from images by introducing PhysPose, a postprocessing optimization method that enforces non-penetration and gravitational constraints, achieving state-of-the-art accuracy on the YCB-Video dataset and improving success rates in a pick-and-place robotics task.
Accurate 6D object pose estimation from images is a key problem in object-centric scene understanding, enabling applications in robotics, augmented reality, and scene reconstruction. Despite recent advances, existing methods often produce physically inconsistent pose estimates, hindering their deployment in real-world scenarios. We introduce PhysPose, a novel approach that integrates physical reasoning into pose estimation through a postprocessing optimization enforcing non-penetration and gravitational constraints. By leveraging scene geometry, PhysPose refines pose estimates to ensure physical plausibility. Our approach achieves state-of-the-art accuracy on the YCB-Video dataset from the BOP benchmark and improves over the state-of-the-art pose estimation methods on the HOPE-Video dataset. Furthermore, we demonstrate its impact in robotics by significantly improving success rates in a challenging pick-and-place task, highlighting the importance of physical consistency in real-world applications.