CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers
This addresses the need for faster and more efficient pose estimation in robotics and AR/VR, though it is incremental as it builds on existing transformer-based refinement approaches.
The paper tackles the problem of slow 6D object pose estimation by introducing CRT-6D, which uses sparse features and lightweight transformers to achieve inference runtimes 2x faster than real-time state-of-the-art methods while supporting up to 21 objects.
Learning based 6D object pose estimation methods rely on computing large intermediate pose representations and/or iteratively refining an initial estimation with a slow render-compare pipeline. This paper introduces a novel method we call Cascaded Pose Refinement Transformers, or CRT-6D. We replace the commonly used dense intermediate representation with a sparse set of features sampled from the feature pyramid we call OSKFs(Object Surface Keypoint Features) where each element corresponds to an object keypoint. We employ lightweight deformable transformers and chain them together to iteratively refine proposed poses over the sampled OSKFs. We achieve inference runtimes 2x faster than the closest real-time state of the art methods while supporting up to 21 objects on a single model. We demonstrate the effectiveness of CRT-6D by performing extensive experiments on the LM-O and YCBV datasets. Compared to real-time methods, we achieve state of the art on LM-O and YCB-V, falling slightly behind methods with inference runtimes one order of magnitude higher. The source code is available at: https://github.com/PedroCastro/CRT-6D