NAISS
SUPR
NAISS Projects
SUPR
Design of Dedicated Visual Neural Architectures by Algorithm Unrolling
Dnr:

NAISS 2026/4-1121

Type:

NAISS Small

Principal Investigator:

Hosea Agure

Affiliation:

Mittuniversitetet

Start Date:

2026-06-10

End Date:

2027-07-01

Primary Classification:

20208: Computer Vision and learning System (Computer Sciences aspects in 10207)

Webpage:

Allocation

Abstract

This project investigates the design of dedicated neural architectures for industrial imaging inverse problems by incorporating modality-specific image formation models and noise characteristics directly into the network structure through algorithm unrolling. By unfolding iterative optimization algorithms into learnable layers, the resulting architectures encode domain knowledge of the forward model, enabling principled regularization and reducing dependence on large training datasets. The approach targets multiple imaging modalities including infrared, multi-spectral, and 3D geometry under challenging conditions such as low light, motion blur, and occlusions, with expected gains of 2–5 dB in visual quality and a fivefold reduction in model parameters, making the architectures suitable for deployment on resource-constrained edge and IoT nodes.