Deep Learning

Self-Supervised Low-Light Quantum RGB Image Demosaicing

Self-Supervised Low-Light Quantum RGB Image Demosaicing

Image acquisition in low-light environments is fundamentally challenging due to the photon-limited nature of the scene, which results in severe noise and incomplete color information. Imaging sensors operating under such conditions require robust …

Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications

Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications

High dynamic range (HDR) imaging is vital for capturing the full range of light tones in scenes, essential for computer vision tasks such as autonomous driving. Standard commercial imaging systems face limitations in capacity for well depth, and …

JR2net: A Joint Non-Linear Representation and Recovery Network for Compressive Spectral Imaging

A joint non-linear representation and recovery network for compressive spectral imaging.

Two-step Deep Learning Framework for Chronic Wounds Detection and Segmentation: A Case Study in Colombia

Two-step deep learning framework for detection and segmentation of chronic wounds presented at STSIVA 2021.

Deep Low-Dimensional Spectral Image Representation for Compressive Spectral Reconstruction

Deep low-dimensional representation for compressive spectral reconstruction presented at IEEE MLSP 2021.