Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation

TL;DR

This paper introduces a 3D object detection method using deep learning to regress descriptors of local RGB-D patches, enabling accurate 6D pose estimation and robust detection across diverse datasets.

Contribution

The paper proposes a novel approach employing a convolutional auto-encoder for local patch descriptor regression, improving 6D pose estimation and scalability over previous methods.

Findings

Outperforms state-of-the-art methods in 3D object detection

Demonstrates strong generalization to unseen data

Provides scalable detection for multiple objects

Abstract

We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder that has been trained on a large collection of random local patches. During testing, scene patch descriptors are matched against a database of synthetic model view patches and cast 6D object votes which are subsequently filtered to refined hypotheses. We evaluate on three datasets to show that our method generalizes well to previously unseen input data, delivers robust detection results that compete with and surpass the state-of-the-art while being scalable in the number of objects.