# DPOD: 6D Pose Object Detector and Refiner

## TL;DR

DPOD is a real-time deep learning framework that estimates 6D object poses from RGB images using dense correspondence maps, outperforming recent methods on synthetic and real data.

## Contribution

The paper introduces DPOD, a novel dense correspondence-based method for 6D pose estimation that leverages synthetic data and includes a deep learning-based pose refinement.

## Key findings

- High-quality 6D poses achieved before and after refinement.
- Superior performance on synthetic and real datasets compared to recent detectors.
- Real-time capability maintained despite high accuracy.

## Abstract

In this paper we present a novel deep learning method for 3D object detection and 6D pose estimation from RGB images. Our method, named DPOD (Dense Pose Object Detector), estimates dense multi-class 2D-3D correspondence maps between an input image and available 3D models. Given the correspondences, a 6DoF pose is computed via PnP and RANSAC. An additional RGB pose refinement of the initial pose estimates is performed using a custom deep learning-based refinement scheme. Our results and comparison to a vast number of related works demonstrate that a large number of correspondences is beneficial for obtaining high-quality 6D poses both before and after refinement. Unlike other methods that mainly use real data for training and do not train on synthetic renderings, we perform evaluation on both synthetic and real training data demonstrating superior results before and after refinement when compared to all recent detectors. While being precise, the presented approach is still real-time capable.