2020/03/07 by Tingbo Hou, Hou, Tingbo, Adel Ahmadyan +7 · 1 citation
Computer Science · Engineering · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robot Manipulation and Learning #Robotics and Sensor-Based Localization #cs.CV
paper · pdf · doi:10.48550/arxiv.2003.03522
arxiv created 2020/03/07 · openalex publication_date 2020/03/07 · arxiv updated 2020/03/10 · openalex created_date 2020/03/13 · openalex updated_date 2026/07/28
In this paper, we address the problem of detecting unseen objects from RGB images and estimating their poses in 3D. We propose two mobile friendly networks: MobilePose-Base and MobilePose-Shape. The former is used when there is only pose supervision, and the latter is for the case when shape supervision is available, even a weak one. We revisit shape features used in previous methods, including segmentation and coordinate map. We explain when and why pixel-level shape supervision can improve pose estimation. Consequently, we add shape prediction as an intermediate layer in the MobilePose-Shape, and let the network learn pose from shape. Our models are trained on mixed real and synthetic data, with weak and noisy shape supervision. They are ultra lightweight that can run in real-time on modern mobile devices (e.g. 36 FPS on Galaxy S20). Comparing with previous single-shot solutions, our method has higher accuracy, while using a significantly smaller model (2~3% in model size or number of parameters).