Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

6DoF Object Pose Estimation via Differentiable Proxy Voting Loss

About

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.

Xin Yu, Zheyu Zhuang, Piotr Koniusz, Hongdong Li• 2020

Related benchmarks

TaskDatasetResultRank
6DoF Pose EstimationOcclusion Linemod (Part I)
Ape19.2
5
6DoF Pose EstimationLinemod (Part II)
Ape Accuracy69.1
4
Showing 2 of 2 rows

Other info

Follow for update