REFLEX: REFLectance EXploration: improving the acquisition, distribution, and exploration of multi-light image collections for surface characterization and analysis

Details
Funded by: MUR PRIN 2022	Reference: REFLEX
Start: 2023-07-09	Duration: 24 Months
Partners
Coordinator: UNIVR	Italy
Contractor: CRS4	Italy

Abstract

The project aims to improve multi-light image acquisition and processing techniques for surface analysis by simplifying setups for acquisition and calibration, possibly using additional capture systems, improving the efficiency and scalability of methods to process, store and distribute captured information, and developing new solutions for visualization. As part of the project, CRS4 coordinates activites will coordinate aimed at studying and prototyping methodologies for the efficient interactive visualization of annotated models derived from multi-light captures and will contribute to the study and development of capture, processing and visualization models and algorithms.

Publications

	[1] Tinsae Dulecha, Leonardo Righetto, Ruggero Pintus, Enrico Gobbetti, and Andrea Giachetti. Disk-NeuralRTI: Optimized NeuralRTI Relighting through Knowledge Distillation. In STAG: Smart Tools and Applications in Graphics, november 2024. To appear.
	[2] Leonardo Righetto, Mohammad Khademizadeh, Andrea Giachetti, Federico Ponchio, Davit Gigilashvili, Fabio Bettio, and Enrico Gobbetti. Efficient and user-friendly visualization of neural relightable images for cultural heritage applications. ACM Journal on Computing and Cultural Heritage (JOCCH), 17, 2024. DOI: 10.1145/3690390. To appear.
	[3] Ruggero Pintus, Antonio Zorcolo, and Enrico Gobbetti. Applying BRDF Monotonicity for Refined Shading Normal Extraction from Multi-Light Image Collections. In The 22nd Eurographics Workshop on Graphics and Cultural Heritage. Pages 1-6, 2024. DOI: 10.2312/gch.20241241.