The challenge of simultaneous object detection and pose estimation: A comparative study

作者：

Highlights：

• Simultaneous object detection and pose estimation problem is addressed.

• Three new deep learning models are evaluated on PASCAL3D+ and ObjectNet3D.

• A thorough comparison with state-of-the-art solutions is carried.

• The new networks achieve state-of-the-art performance on both datasets

• Decoupling the detection from the viewpoint estimation have benefits.

摘要

•Simultaneous object detection and pose estimation problem is addressed.•Three new deep learning models are evaluated on PASCAL3D+ and ObjectNet3D.•A thorough comparison with state-of-the-art solutions is carried.•The new networks achieve state-of-the-art performance on both datasets•Decoupling the detection from the viewpoint estimation have benefits.

论文关键词：Pose estimation,Viewpoint estimation,Object detection,Deep learning,Convolutional neural network

论文评审过程：Received 12 January 2018, Accepted 14 September 2018, Available online 25 September 2018, Version of Record 5 October 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.09.013