AIN2: Artificial Intelligence for Indoor Digital Twins

Funded by: QNRFReference: NPRP15S-0405-210132
Start: 2023-07-09Duration: 28 Months
Coordinator: HBKUQatar
Contractor: CRS4Italy


While the area of structured indoor reconstruction has witnessed substantial progress in the past decade, current solutions are mostly limited to relatively simple environments with constrained shapes and provide very limited opportunities for seamlessly going from captured data to a dynamically modifiable representation. In AIN2, we aim to substantially advance this research field by proposing specialized solutions for rapidly capturing, exploring, and visually editing indoor environment starting from panoramic images. The project will tackle fundamental problems in the field of reality-based indoor reconstruction, modeling, exploration, leading to new methods, algorithms, and reference implementations.


[1] Muhammad Tukur, Atiq Ur Rehman, Giovanni Pintore, Enrico Gobbetti, Jens Schneider, and Marco Agus. PanoStyle: Semantic, Geometry-Aware and Shading Independent Photorealistic Style Transfer for Indoor Panoramic Scenes. In Proc. of the First Computer Vision Aided Architectural Design Workshop, International Conference of Computer Vision (ICCVW). Pages 1553-1564, October 2023. 
[2] Giovanni Pintore, Alberto Jaspe Villanueva, Markus Hadwiget, Enrico Gobbetti, Jens Schneider, and Marco Agus. PanoVerse: automatic generation of stereoscopic environments from single indoor panoramic images for Metaverse applications. In Proc. Web3D 2023 - 28th International ACM Conference on 3D Web Technology, October 2023. DOI: 10.1145/3611314.3615914. Honorable mention award in the best paper category at Web3D 2023. 
[3] Giovanni Pintore, Fabio Bettio, Marco Agus, and Enrico Gobbetti. Deep scene synthesis of Atlanta-world interiors from a single omnidirectional image. IEEE Transactions on Visualization and Computer Graphics, 29, November 2023. DOI: 10.1109/TVCG.2023.3320219. Proc. ISMAR..