Deep 3D World Models for Multi-Image Super-Resolution Beyond Optical Flow

no code implementations • 30 Jan 2024 • Luca Savant Aira, Diego Valsesia, Andrea Bordone Molini, Giulia Fracastoro, Enrico Magli, Andrea Mirabile

Multi-image super-resolution (MISR) allows to increase the spatial resolution of a low-resolution (LR) acquisition by combining multiple images carrying complementary information in the form of sub-pixel offsets in the scene sampling, and can be significantly more effective than its single-image counterpart.

Image Registration Image Super-Resolution +1

On Deep Neural Network Calibration by Regularization and its Impact on Refinement

no code implementations • 17 Jun 2021 • Aditya Singh, Alessandro Bay, Biswa Sengupta, Andrea Mirabile

We find that many calibration approaches with the likes of label smoothing, mixup etc.

Exploring Target Driven Image Classification

no code implementations • 1 Jan 2021 • Aditya Singh, Alessandro Bay, Andrea Mirabile

We argue that, for any arbitrary category $\mathit{\tilde{y}}$, the composed question 'Is this image of an object category $\mathit{\tilde{y}}$' serves as a viable approach for image classification via.

Classification Fine-Grained Image Classification +1

Assessing The Importance Of Colours For CNNs In Object Recognition

no code implementations • NeurIPS Workshop SVRHM 2020 • Aditya Singh, Alessandro Bay, Andrea Mirabile

In this paper, we empirically investigate the importance of colours in object recognition for CNNs.

Fine-Grained Image Classification General Classification +2