6DoF Object Pose Estimation via Differentiable Proxy Voting Loss
This work solves pose estimation for robotics or AR applications, but it is incremental as it builds on existing vector-field methods.
The paper tackles the challenge of 6DOF object pose estimation from single images by addressing errors in vector-field keypoint voting due to distance effects, resulting in significant performance improvements and faster training convergence on LINEMOD and Occlusion LINEMOD datasets.
Estimating a 6DOF object pose from a single image is very challenging due to occlusions or textureless appearances. Vector-field based keypoint voting has demonstrated its effectiveness and superiority on tackling those issues. However, direct regression of vector-fields neglects that the distances between pixels and keypoints also affect the deviations of hypotheses dramatically. In other words, small errors in direction vectors may generate severely deviated hypotheses when pixels are far away from a keypoint. In this paper, we aim to reduce such errors by incorporating the distances between pixels and keypoints into our objective. To this end, we develop a simple yet effective differentiable proxy voting loss (DPVL) which mimics the hypothesis selection in the voting procedure. By exploiting our voting loss, we are able to train our network in an end-to-end manner. Experiments on widely used datasets, i.e., LINEMOD and Occlusion LINEMOD, manifest that our DPVL improves pose estimation performance significantly and speeds up the training convergence.