Review on 6D Object Pose Estimation with the focus on Indoor Scene Understanding

Abstract

6D object pose estimation problem has been extensively studied in the field of Computer Vision and Robotics. It has wide range of applications such as robot manipulation, augmented reality, and 3D scene understanding. With the advent of Deep Learning, many breakthroughs have been made; however, approaches continue to struggle when they encounter unseen instances, new categories, or real-world challenges such as cluttered backgrounds and occlusions. In this study, we will explore the available methods based on input modality, problem formulation, and whether it is a category-level or instance-level approach. As a part of our discussion, we will focus on how 6D object pose estimation can be used for understanding 3D scenes.

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Deep Closest Point: Learning Representations for Point Cloud Registration
• Boosting 3D Object Detection via Object-Focused Image Fusion
• PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
• CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration
• Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
• Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challenges
• Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation
• 3DPVNet: Patch-level 3D Hough Voting Network for 6D Pose Estimation