Recently, Deep Learning-based methods for converting 8-bit images and videos into high dynamic range (HDR) content have become very popular.
These methods manage to fill over-exposed areas convincingly both in terms of details and dynamic range.
To be effective, these deep learning methods need to learn from large datasets and transfer this knowledge to the network weights.
In this talk, we will introduce a different point of view on this matter. What can we learn from the input itself to achieve HDR imaging?
30/4/2025 - 14:00 - sala verde
© 2025 | Università degli studi di Verona
******** CSS e script comuni siti DOL - frase 9957 ********
