Spectral 3D Computer Vision -- A Review
Yajie Sun, Ali Zia, Vivien Rolland, Charissa Yu, Jun Zhou

TL;DR
Spectral 3D computer vision integrates spectral and geometric data to enhance understanding of physical object properties, advancing traditional methods and enabling diverse applications like agriculture and cultural heritage preservation.
Contribution
This survey provides a comprehensive overview and taxonomy of spectral 3D vision methods, highlighting its applications, challenges, and future research directions.
Findings
Unified taxonomy of spectral 3D methods
Identification of key application areas
Discussion of future challenges and prospects
Abstract
Spectral 3D computer vision examines both the geometric and spectral properties of objects. It provides a deeper understanding of an object's physical properties by providing information from narrow bands in various regions of the electromagnetic spectrum. Mapping the spectral information onto the 3D model reveals changes in the spectra-structure space or enhances 3D representations with properties such as reflectance, chromatic aberration, and varying defocus blur. This emerging paradigm advances traditional computer vision and opens new avenues of research in 3D structure, depth estimation, motion analysis, and more. It has found applications in areas such as smart agriculture, environment monitoring, building inspection, geological exploration, and digital cultural heritage records. This survey offers a comprehensive overview of spectral 3D computer vision, including a unified…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsIndustrial Vision Systems and Defect Detection · 3D Surveying and Cultural Heritage · Advanced Image Fusion Techniques
