Convolutional Neural Networks for joint object detection and pose estimation: A comparative study

Abstract

In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose. We identify different feature representations of oriented objects, and energies that lead a network to learn this representations. The choice of the representation is crucial since the pose of an object has a natural, continuous structure while its category is a discrete variable. We evaluate the different approaches on the joint object detection and pose estimation task of the Pascal3D+ benchmark using Average Viewpoint Precision. We show that a classification approach on discretized viewpoints achieves state-of-the-art performance for joint object detection and pose estimation, and significantly outperforms existing baselines on this benchmark.

References in corpus (2)

• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Rich feature hierarchies for accurate object detection and semantic segmentation

Cited by in corpus (6)

• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• 6-DoF Object Pose from Semantic Keypoints
• Crafting a multi-task CNN for viewpoint estimation
• Semantic keypoint-based pose estimation from single RGB frames
• A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images
• Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images