The 3D survey module aims to provide knowledge of the theoretical principles and practical applications of technologies such as LiDAR and photogrammetry based on Structure from Motion (SfM) algorithms for the generation of point clouds, high-resolution three-dimensional models, and metric products intended for technical documentation. The training pathway integrates data acquisition, processing, and point cloud management phases, leading to the production of metrically reliable 3D models suitable also for use in virtual reality environments. Innovative applications of Artificial Intelligence will also be explored, with particular attention to Gaussian Splatting techniques for the advanced representation and visualization of three-dimensional scenes. The course combines theoretical lectures with practical field and laboratory exercises using dedicated software, providing operational skills that are immediately applicable in the fields of engineering and architecture.

At the end of the 3D survey module, students will be able to: • Understand the basic theoretical principles underlying LiDAR technologies and Structure from Motion (SfM) photogrammetry. • Plan and carry out 3D data acquisition campaigns according to documentation and modeling objectives. • Process and manage point clouds, optimizing their quality, accuracy, and organization. • Generate metrically reliable, high-resolution three-dimensional models from LiDAR and photogrammetric data. • Produce technical outputs and 3D models suitable for documentation and representation in engineering and architectural contexts. • Understand and critically evaluate innovative Artificial Intelligence applications, with particular reference to Gaussian Splatting techniques for advanced three-dimensional scene representation. • Operate specialized software for surveying, data processing, and 3D visualization, applying appropriate and informed methodologies.

Basic skills acquired during the first years of Architecture and Engineering degree programs.

Theoretical foundations of 3D metric survey (3 hours) Digital Photogrammetry and Structure from Motion (10 hours) • Basic principles (3 hours) • Data acquisition, processing, and review (7 hours) LiDAR (10 hours) • Basic principles (3 hours) • Data acquisition, processing, and review (7 hours) AI and New Frontiers in 3D Data Extraction (7 hours) • Basic principles (2 hours) • Data processing and review (5 hours) Total 30 hours

50% of the teaching activities will be delivered in person and 50% online , of which a maximum of 20% will be asynchronous.

Luhmann, T., Robson, S., Kyle, S., & Boehm, J. (2020). Close-Range Photogrammetry and 3D Imaging (2nd ed.). Berlin/Boston: De Gruyter. Shan, J., & Toth, C. K. (a cura di) (2018). Topographic Laser Ranging and Scanning: Principles and Processing (2nd ed.). Boca Raton: CRC Press. Historic England (2018). 3D Laser Scanning for Heritage: Advice and Guidance on the Use of Laser Scanning in Archaeology and Architecture. Swindon: Historic England. Kerbl, B., Kopanas, G., Leimkühler, T., & Drettakis, G. (2023). 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics (SIGGRAPH 2023).

Slides; Video lezioni dell’anno corrente;

Modalita di esame: Elaborato scritto prodotto in gruppo; Accertamento (esame senza voto);

Exam: Group essay; Check;

...

Gli studenti e le studentesse con disabilita o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unita Special Needs, al fine di permettere al/la docente la declinazione piu idonea in riferimento alla specifica tipologia di esame.