Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations

TL;DR

This paper presents a novel method for 3D pose estimation from color images that leverages paired RGB-D data and synthetic depth images, eliminating the need for manual annotations and achieving competitive results.

Contribution

The approach introduces a way to learn 3D pose estimation from color images without manual annotations by aligning synthetic and real depth images using paired RGB-D data.

Findings

Achieves performance comparable to state-of-the-art methods.

Does not require manual annotations for color images.

Effective for both hand and object pose estimation.

Abstract

We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images captured with an RGB-D camera. We jointly learn the pose from synthetic depth images that are easy to generate, and learn to align these synthetic depth images with the real depth images. We show our approach for the task of 3D hand pose estimation and 3D object pose estimation, both from color images only. Our method achieves performances comparable to state-of-the-art methods on popular benchmark datasets, without requiring any annotations for the color images.