Micro-object pose estimation with sim-to-real transfer learning using small dataset

High-resolution scanning tunnelling microscopy is a state-of-the-art imaging technique at the nanometer scale. This work presents a novel deep learning approach for 3D pose estimation of micro/nano-objects, particularly useful in regimes of limited experimental data.

Bibliographic Details
Main Authors: Dandan Zhang, Antoine Barbot, Florent Seichepine, Frank P.-W. Lo, Wenjia Bai, Guang-Zhong Yang, Benny Lo
Format: Article
Language:English
Published: Nature Portfolio 2022-04-01
Series:Communications Physics
Online Access:https://doi.org/10.1038/s42005-022-00844-z