Saved in:
Bibliographic Details
Main Authors: Stathatos, Suzanne, Hobley, Michael, Perona, Pietro, Marks, Markus
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00161
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914088741765120
author Stathatos, Suzanne
Hobley, Michael
Perona, Pietro
Marks, Markus
author_facet Stathatos, Suzanne
Hobley, Michael
Perona, Pietro
Marks, Markus
contents Low signal-to-noise ratio videos -- such as those from underwater sonar, ultrasound, and microscopy -- pose significant challenges for computer vision models, particularly when paired clean imagery is unavailable. We present Spatiotemporal Augmentations and denoising in Video for Downstream Tasks (SAVeD), a novel self-supervised method that denoises low-SNR sensor videos using only raw noisy data. By leveraging distinctions between foreground and background motion and exaggerating objects with stronger motion signal, SAVeD enhances foreground object visibility and reduces background and camera noise without requiring clean video. SAVeD has a set of architectural optimizations that lead to faster throughput, training, and inference than existing deep learning methods. We also introduce a new denoising metric, FBD, which indicates foreground-background divergence for detection datasets without requiring clean imagery. Our approach achieves state-of-the-art results for classification, detection, tracking, and counting tasks, and it does so with fewer training resource requirements than existing deep-learning-based denoising methods. Project page: https://suzanne-stathatos.github.io/SAVeD Code page: https://github.com/suzanne-stathatos/SAVeD
format Preprint
id arxiv_https___arxiv_org_abs_2504_00161
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance
Stathatos, Suzanne
Hobley, Michael
Perona, Pietro
Marks, Markus
Computer Vision and Pattern Recognition
Low signal-to-noise ratio videos -- such as those from underwater sonar, ultrasound, and microscopy -- pose significant challenges for computer vision models, particularly when paired clean imagery is unavailable. We present Spatiotemporal Augmentations and denoising in Video for Downstream Tasks (SAVeD), a novel self-supervised method that denoises low-SNR sensor videos using only raw noisy data. By leveraging distinctions between foreground and background motion and exaggerating objects with stronger motion signal, SAVeD enhances foreground object visibility and reduces background and camera noise without requiring clean video. SAVeD has a set of architectural optimizations that lead to faster throughput, training, and inference than existing deep learning methods. We also introduce a new denoising metric, FBD, which indicates foreground-background divergence for detection datasets without requiring clean imagery. Our approach achieves state-of-the-art results for classification, detection, tracking, and counting tasks, and it does so with fewer training resource requirements than existing deep-learning-based denoising methods. Project page: https://suzanne-stathatos.github.io/SAVeD Code page: https://github.com/suzanne-stathatos/SAVeD
title SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.00161