Object aspect classification and 6DoF pose estimation

作者：

Highlights：

• We introduce a simple aspect-representation for 3D objects for 6DoF pose estimation.

• This representation is used to cluster appearances of an object as aspects.

• Proposed model predicts both the aspect of a given object and the semantic-key points.

• Multi-tasking to high confidence key-point vectors hence more accurate results.

• Proposed method is significantly faster due to small backbone and limited PnP Space.

摘要

Highlights•We introduce a simple aspect-representation for 3D objects for 6DoF pose estimation.•This representation is used to cluster appearances of an object as aspects.•Proposed model predicts both the aspect of a given object and the semantic-key points.•Multi-tasking to high confidence key-point vectors hence more accurate results.•Proposed method is significantly faster due to small backbone and limited PnP Space.

论文关键词：Computer vision,Object pose estimation,Aspect graph,Deep learning

论文评审过程：Received 11 May 2021, Revised 16 December 2021, Accepted 25 May 2022, Available online 1 June 2022, Version of Record 11 June 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104495