DeepIM: Deep Iterative Matching for 6D Pose Estimation
This addresses the need for accurate object pose estimation in applications like robot manipulation and virtual reality, representing a strong specific gain in the domain.
The paper tackles the problem of 6D pose estimation from images by proposing DeepIM, a deep neural network that iteratively refines pose estimates by matching rendered images against observed ones, achieving large improvements over state-of-the-art methods on two benchmarks.
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the observed image can produce accurate results. In this work, we propose a novel deep neural network for 6D pose matching named DeepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using an untangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks for 6D pose estimation demonstrate that DeepIM achieves large improvements over state-of-the-art methods. We furthermore show that DeepIM is able to match previously unseen objects.