Multi-Level Fusion for Burst Super-Resolution with Deep Permutation-Invariant Conditioning
Martina Cilia, Diego Valsesia, Giulia Fracastoro, Enrico Magli
Abstract
Developing deep learning techniques for super-resolving bursts of images acquired by mobile cameras is a topic that has recently gained significant interest. This topic fits the general problem of learning-based multi-image super-resolution (SR), which, contrary to its sibling single-image SR, has so far received little attention despite its potential. In this work, we introduce a neural network architecture for burst SR, called MLB-FuseNet (Multi-Level Burst Fusion Network), that is capable of extracting features in a manner that is invariant to permutations in the burst and to progressively condition features extracted from a reference image. Permutation invariance is desirable as it is known that the order of images in a burst does not matter in this problem, but its study has so far been neglected. Moreover, we also introduce a module exploiting a polyphase decomposition to improve feature extraction from mosaiced raw images. Results show an improvement over the state of the art on the BurstSR dataset – a recent and popular benchmark for this problem.
BibTeX
@inproceedings{icassp2023_multilevelfusion,
title = {Multi-Level Fusion for Burst Super-Resolution with Deep Permutation-Invariant Conditioning},
author = {Martina Cilia and Diego Valsesia and Giulia Fracastoro and Enrico Magli},
booktitle = {ICASSP 2023},
year = {2023}
}