Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach

Zhihao Li, Yufei Wang, Alex Kot, Bihan Wen
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28706-28716, 2024.

Abstract

Raw images offer unique advantages in many low-level visual tasks due to their unprocessed nature. However, this unprocessed state accentuates noise, making raw images challenging to compress effectively. Current compression methods often overlook the ubiquitous noise in raw space, leading to increased bitrates and reduced quality. In this paper, we propose a novel raw image compression scheme that selectively compresses the noise-free component of the input, while discarding its real noise using a self-supervised approach. By excluding noise from the bitstream, both the coding efficiency and reconstruction quality are significantly enhanced. We curate an full-day dataset of raw images with calibrated noise parameters and reference images to evaluate the performance of models under a wide range of input signal-noise ratios. Experimental results demonstrate that our method surpasses existing compression techniques, achieving a more advantageous rate-distortion balance with improvements ranging from +2 to +10dB and yielding a bit saving of 2 to 50 times. The code will be released upon paper acceptance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-li24bl, title = {Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach}, author = {Li, Zhihao and Wang, Yufei and Kot, Alex and Wen, Bihan}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {28706--28716}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/li24bl/li24bl.pdf}, url = {https://proceedings.mlr.press/v235/li24bl.html}, abstract = {Raw images offer unique advantages in many low-level visual tasks due to their unprocessed nature. However, this unprocessed state accentuates noise, making raw images challenging to compress effectively. Current compression methods often overlook the ubiquitous noise in raw space, leading to increased bitrates and reduced quality. In this paper, we propose a novel raw image compression scheme that selectively compresses the noise-free component of the input, while discarding its real noise using a self-supervised approach. By excluding noise from the bitstream, both the coding efficiency and reconstruction quality are significantly enhanced. We curate an full-day dataset of raw images with calibrated noise parameters and reference images to evaluate the performance of models under a wide range of input signal-noise ratios. Experimental results demonstrate that our method surpasses existing compression techniques, achieving a more advantageous rate-distortion balance with improvements ranging from +2 to +10dB and yielding a bit saving of 2 to 50 times. The code will be released upon paper acceptance.} }
Endnote
%0 Conference Paper %T Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach %A Zhihao Li %A Yufei Wang %A Alex Kot %A Bihan Wen %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-li24bl %I PMLR %P 28706--28716 %U https://proceedings.mlr.press/v235/li24bl.html %V 235 %X Raw images offer unique advantages in many low-level visual tasks due to their unprocessed nature. However, this unprocessed state accentuates noise, making raw images challenging to compress effectively. Current compression methods often overlook the ubiquitous noise in raw space, leading to increased bitrates and reduced quality. In this paper, we propose a novel raw image compression scheme that selectively compresses the noise-free component of the input, while discarding its real noise using a self-supervised approach. By excluding noise from the bitstream, both the coding efficiency and reconstruction quality are significantly enhanced. We curate an full-day dataset of raw images with calibrated noise parameters and reference images to evaluate the performance of models under a wide range of input signal-noise ratios. Experimental results demonstrate that our method surpasses existing compression techniques, achieving a more advantageous rate-distortion balance with improvements ranging from +2 to +10dB and yielding a bit saving of 2 to 50 times. The code will be released upon paper acceptance.
APA
Li, Z., Wang, Y., Kot, A. & Wen, B.. (2024). Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:28706-28716 Available from https://proceedings.mlr.press/v235/li24bl.html.

Related Material