データ不足環境での6D物体姿勢推定のための視点フロー集約
Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
合成画像のみ、または少数の実画像で学習できる6D姿勢推定手法を提案。粗い姿勢推定から描画画像と実画像間の密な2D対応場を予測し姿勢補正を行うことで、ドメインシフトに強く、実画像20枚程度で従来手法を大きく上回る。
著者: Yinlin Hu, Pascal Fua, Mathieu Salzmann
分類: cs.CV, cs.RO
原文アブストラクト
Most recent 6D object pose estimation methods, including unsupervised ones, require many real training images. Unfortunately, for some applications, such as those in space or deep under water, acquiring real images, even unannotated, is virtually impossible. In this paper, we propose a method that can be trained solely on synthetic images, or optionally using a few additional real ones. Given a rough pose estimate obtained from a first network, it uses a second network to predict a dense 2D correspondence field between the image rendered using the rough pose and the real image and infers the required pose correction. This approach is much less sensitive to the domain shift between synthetic and real images than state-of-the-art methods. It performs on par with methods that require annotated real images for training when not using any, and outperforms them considerably when using as few as twenty real images.
