Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk

Romain Brégier 1, 2 Frédéric Devernay 2 Laetitia Leyrit 3 James L. Crowley 4
2 IMAGINE - Intuitive Modeling and Animation for Interactive Graphics & Narrative Environments
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
4 PERVASIVE INTERACTION
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : While 3D object detection and pose estimation has been studied for a long time, its evaluation is not yet completely satisfactory. Indeed, existing datasets typically consist in numerous acquisitions of only a few scenes because of the tediousness of pose annotation, and existing evaluation protocols cannot handle properly objects with symmetries. This work aims at addressing those two points. We first present automatic techniques to produce fully annotated RGBD data of many object instances in arbitrary poses, with which we produce a dataset of thousands of independent scenes of bulk parts composed of both real and synthetic images. We then propose a consistent evaluation methodology suitable for any rigid object, regardless of its symmetries. We illustrate it with two reference object detection and pose estimation methods on different objects, and show that incorporating symmetry considerations into pose estimation methods themselves can lead to significant performance gains. The proposed dataset is available at http://rbregier.github.io/dataset2017.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-01819659
Contributor : Romain Brégier <>
Submitted on : Wednesday, June 20, 2018 - 5:40:37 PM
Last modification on : Thursday, May 2, 2019 - 3:30:31 PM
Long-term archiving on : Tuesday, September 25, 2018 - 8:27:19 PM

Identifiers

Citation

Romain Brégier, Frédéric Devernay, Laetitia Leyrit, James L. Crowley. Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk. 2017 IEEE International Conference on Computer Vision Workshop (ICCVW), Oct 2017, Venice, France. pp.2209-2218, ⟨10.1109/ICCVW.2017.258⟩. ⟨hal-01819659⟩

Share

Metrics

Record views

247

Files downloads

358