2022/07/01 by Jun Wu, Wu, Jun, Lilu Liu +5
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Robot Manipulation and Learning #Robotics (cs.RO) #cs.CV #cs.RO
paper · pdf · doi:10.48550/arxiv.2207.00260
arXiv admin note: text overlap with arXiv:2109.12266
arxiv created 2022/07/01 · openalex publication_date 2022/07/01 · arxiv updated 2022/07/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Current RGB-based 6D object pose estimation methods have achieved noticeable performance on datasets and real world applications. However, predicting 6D pose from single 2D image features is susceptible to disturbance from changing of environment and textureless or resemblant object surfaces. Hence, RGB-based methods generally achieve less competitive results than RGBD-based methods, which deploy both image features and 3D structure features. To narrow down this performance gap, this paper proposes a framework for 6D object pose estimation that learns implicit 3D information from 2 RGB images. Combining the learned 3D information and 2D image features, we establish more stable correspondence between the scene and the object models. To seek for the methods best utilizing 3D information from RGB inputs, we conduct an investigation on three different approaches, including Early- Fusion, Mid-Fusion, and Late-Fusion. We ascertain the Mid- Fusion approach is the best approach to restore the most precise 3D keypoints useful for object pose estimation. The experiments show that our method outperforms state-of-the-art RGB-based methods, and achieves comparable results with RGBD-based methods.