3 papers
cs.CV2025
Addressing the Depth-of-Field Constraint: A New Paradigm for High Resolution Multi-Focus Image Fusion
Luca Piano, Peng Huanwen, Radu Ciprian Bilcu
Multi-focus image fusion (MFIF) addresses the depth-of-field (DOF) limitations of optical lenses, where only objects within a specific range appear sharp. Although traditional and…
cs.CV2024
For a semiotic AI: Bridging computer vision and visual semiotics for computational observation of large scale facial image archives
Lia Morra, Antonio Santangelo, Pietro Basci +4
Social networks are creating a digital world in which the cognitive, emotional, and pragmatic value of the imagery of human faces and bodies is arguably changing. However, research…
cs.LG2024
Toward a Realistic Benchmark for Out-of-Distribution Detection
Pietro Recalcati, Fabio Garcea, Luca Piano +2
Deep neural networks are increasingly used in a wide range of technologies and services, but remain highly susceptible to out-of-distribution (OOD) samples, that is, drawn from a d…