Translator Disclaimer
Presentation + Paper
10 October 2020 PP-Net: simultaneous pose and shape reconstruction from a single depth map
Author Affiliations +
Abstract
Complete 3D information of the object is required in many fields. However, single-view observation always leads to the loss of 3D information. We introduce a learning based approach to simultaneously estimate the pose and shape of a given object from a single depth map.To address the problem, a depth map is firstly converted to be the corresponding partial point cloud, then an autoencoder-based network is proposed to learn this pose estimation as well as shape completion process. In the learning paradigm ,we utilize a novel pose representation, structured point list (SPL) to describe objects pose, which enables the network to understand the pose of the input object relative to the perspective. Compared with directly shape reconstruction, we find that adding SPL estimation as an intermediate supervision can both improve the accuracy of reconstruction and accelerate the convergence speed for training. Our method achieved SOTA results on both rigid and non-rigid objects reconstructions.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zimeng Zhao, Kanjian Zhang, and Yangang Wang "PP-Net: simultaneous pose and shape reconstruction from a single depth map", Proc. SPIE 11550, Optoelectronic Imaging and Multimedia Technology VII, 115500N (10 October 2020); https://doi.org/10.1117/12.2572825
PROCEEDINGS
13 PAGES + PRESENTATION

SHARE
Advertisement
Advertisement
Back to Top