English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Despite the significant progress in six degrees-of-freedom (6DoF) object poseestimation, existing methods have limited applicability in real-world scenariosinvolving embodied agents and downstream 3D vision tasks. These limitationsmainly come from the necessity of 3D models, closed-category detection, and alarge number of densely annotated support views. To mitigate this issue, wepropose a general paradigm for object pose estimation, called Promptable ObjectPose Estimation (POPE). The proposed approach POPE enables zero-shot 6DoFobject pose estimation for any target object in any scene, while only a singlereference is adopted as the support view. To achieve this, POPE leverages thepower of the pre-trained large-scale 2D foundation model, employs a frameworkwith hierarchical feature representation and 3D geometry principles. Moreover,it estimates the relative camera pose between object prompts and the targetobject in new views, enabling both two-view and multi-view 6DoF pose estimationtasks. Comprehensive experimental results demonstrate that POPE exhibitsunrivaled robust performance in zero-shot settings, by achieving a significantreduction in the averaged Median Pose Error by 52.38% and 50.47% on the LINEMODand OnePose datasets, respectively. We also conduct more challenging testingsin causally captured images (see Figure 1), which further demonstrates therobustness of POPE. Project page can be found withhttps://paulpanwang.github.io/POPE/.

POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference