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

2018/01/01 by Mahdi Rad, Rad, Mahdi, Markus Oberweger +3 · 1 citation
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Human Pose and Action Recognition #Robot Manipulation and Learning

paper · pdf · doi:10.48550/arxiv.1810.03707

openalex publication_date 2018/10/08 · openalex created_date 2022/11/11 · openalex updated_date 2026/07/28

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.

Citations

• Domain Adaptation via Transfer Component Analysis
• Generative Adversarial Networks
• Auto-Encoding Variational Bayes
• Domain Generalization via Invariant Feature Representation
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Domain Separation Networks
• 3D Hand Pose Tracking and Estimation Using Stereo Matching
• A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image

Cited by

• Sparse Pose Trajectory Completion

Related

• RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images
• Learning Local RGB-to-CAD Correspondences for Object Pose Estimation
• Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images
• A Dual-Source Approach for 3D Pose Estimation from a Single Image
• 3D Human Pose Estimation in RGBD Images for Robotic Task Learning