Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images

TL;DR

This paper introduces a feature mapping approach that leverages synthetic images to train a deep network for fast, accurate 3D pose inference from real images, outperforming existing methods on benchmark datasets.

Contribution

The paper presents a general network-based method that maps features from real to synthetic images, enabling effective training with synthetic data for 3D pose estimation.

Findings

Outperforms state-of-the-art on LINEMOD dataset

Achieves faster inference than exemplar-based methods

Demonstrates high accuracy on NYU hand pose dataset

Abstract

We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy to create a virtually infinite training set made of such images, while capturing and annotating real images can be very cumbersome. However, synthetic images do not resemble real images exactly, and using them for training can result in suboptimal performance. It was recently shown that for exemplar-based approaches, it is possible to learn a mapping from the exemplar representations of real images to the exemplar representations of synthetic images. In this paper, we show that this approach is more general, and that a network can also be applied after the mapping to infer a 3D pose: At run time, given a real image of the target object, we first compute the features for the image, map them to the feature space of synthetic images, and finally use the resulting features as input to another network which predicts the 3D pose. Since this network can be trained very effectively by using synthetic images, it performs very well in practice, and inference is faster and more accurate than with an exemplar-based approach. We demonstrate our approach on the LINEMOD dataset for 3D object pose estimation from color images, and the NYU dataset for 3D hand pose estimation from depth maps. We show that it allows us to outperform the state-of-the-art on both datasets.