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

TL;DR

This review discusses 6D object pose estimation techniques, emphasizing their applications in indoor scene understanding, challenges faced in real-world scenarios, and categorization based on input modalities and problem formulation.

Contribution

It provides a comprehensive overview of existing methods, analyzing their strengths and limitations in indoor scene understanding and categorization.

Findings

Deep learning has advanced 6D pose estimation but struggles with unseen instances and clutter.

Category-level and instance-level approaches have different advantages and challenges.

Understanding 3D scenes benefits from pose estimation techniques despite real-world challenges.

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.