Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging

TMLR Paper4698 Authors

Abstract: Learning based methods are now ubiquitous for solving inverse problems, but their deployment in real-world applications is often hindered by the lack of ground truth references for training. Recent self-supervised learning strategies offer a promising alternative, avoiding the need for ground truth. However, most existing methods are limited to linear inverse problems. This work extends self-supervised learning to the non-linear problem of recovering audio and images from clipped measurements, by assuming that the signal distribution is approximately invariant to changes in amplitude. We provide sufficient conditions for learning to reconstruct from saturated signals alone and a self supervised loss that can be used to train reconstruction networks. Experiments on both audio and image data show that the proposed approach performs on par with fully supervised approaches, despite relying solely on clipped measurements for training.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Fernando_Perez-Cruz1

Submission Number: 4698