A5062456698- Advanced MRI Techniques and Applications
- Sparse and Compressive Sensing Techniques
- Atomic and Subatomic Physics Research
- Industrial Vision Systems and Defect Detection
- Neural Networks and Applications
- Image Processing Techniques and Applications
- Optical Imaging and Spectroscopy Techniques
- Photoacoustic and Ultrasonic Imaging
- Fault Detection and Control Systems
- Medical Image Segmentation Techniques
- Image and Signal Denoising Methods
- Medical Imaging Techniques and Applications
- Sensor Technology and Measurement Systems
Industrial University of Santander
2022-2025
In computational optical imaging and wireless communications, signals are acquired through linear coded noisy projections, which recovered algorithms. Deep model-based approaches, i.e., neural networks incorporating the sensing operators, state-of-the-art for signal recovery. However, these methods require exact knowledge of operator, is often unavailable in practice, leading to performance degradation. Consequently, we propose a new recovery paradigm based on distillation. A teacher model,...
Deep-learning (DL)-based image deconvolution (ID) has exhibited remarkable recovery performance, surpassing traditional linear methods. However, unlike ID approaches that rely on analytical properties of the point spread function (PSF) to achieve high performance - such as specific spectrum or small conditional numbers in convolution matrix DL techniques lack quantifiable metrics for evaluating PSF suitability DL-assisted recovery. Aiming enhance quality, we propose a metric employs...
We propose a methodology for reconstruction of compressive spectral imaging from an uncalibrated optical system, where the propagation model is learned and included as regularizer to improve quality.
A compressive image recovery method that includes a regularizer in the baseline deep prior is proposed to consider calibration sensing model mismatch.