3D Registration for Self-Occluded Objects in Context

TL;DR

This paper presents a novel deep learning framework for 3D registration and pose estimation of self-occluded objects from 2.5D sensor data, overcoming challenges of outliers and partial observations.

Contribution

It introduces the first end-to-end deep learning method for 3D registration of self-occluded objects, combining segmentation and pose estimation in a one-shot process.

Findings

Outperforms state-of-the-art traditional methods

Effective handling of outliers and partial data

Efficient training with rendering-based strategy

Abstract

While much progress has been made on the task of 3D point cloud registration, there still exists no learning-based method able to estimate the 6D pose of an object observed by a 2.5D sensor in a scene. The challenges of this scenario include the fact that most measurements are outliers depicting the object's surrounding context, and the mismatch between the complete 3D object model and its self-occluded observations. We introduce the first deep learning framework capable of effectively handling this scenario. Our method consists of an instance segmentation module followed by a pose estimation one. It allows us to perform 3D registration in a one-shot manner, without requiring an expensive iterative procedure. We further develop an on-the-fly rendering-based training strategy that is both time- and memory-efficient. Our experiments evidence the superiority of our approach over the state-of-the-art traditional and learning-based 3D registration methods.