Robotic assisted 3D reconstruction with high resolution textures

Geng Lyu*, Wenbin Hu, Yang Luo

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

5 Downloads (Pure)

Abstract

3D reconstruction remains a challenging scientific problem,
encompassing various fields such as computer-aided geometric design,
computer vision, computer graphics, and computational science. Traditional methods, whether active using mechanical or radiometric rangefinders or passive based on computer vision, predominantly focus on recovering 3D geometry rather than textures. However, highly detailed textures
are crucial in fields requiring precise representation, such as digital museums and medical imaging. Recent advancements in 3D reconstruction
based on macro photography and focal stacking have yielded impressive
results. Building on these advancements, we aim to refine the process
further. Inspired by the renowned Digital Michelangelo Project, which features well-designed hardware and software, we propose using roboticassisted image capturing for microscopic 3D reconstruction. We have
designed and implemented a robotic-assisted 3D reconstruction pipeline that captures microscopic image sets from subject surfaces, generating 3D reconstructed surfaces with microscopic-level details. This approach promises to enhance the precision and detail of 3D reconstructions, making them more suitable for applications requiring high fidelity and accuracy.
Original languageEnglish
Title of host publicationInternational Conference on Intelligent Manufacturing and Robotics 2024
Subtitle of host publicationICiMR 2024
PublisherSpringer
Publication statusAccepted/In press - 2024
Event2nd International Conference on Intelligent Manufacturing and Robotics (ICiMR) - Taicang, China
Duration: 22 Aug 202423 Aug 2024

Conference

Conference2nd International Conference on Intelligent Manufacturing and Robotics (ICiMR)
Country/TerritoryChina
Period22/08/2423/08/24

Fingerprint

Dive into the research topics of 'Robotic assisted 3D reconstruction with high resolution textures'. Together they form a unique fingerprint.

Cite this