On the Importance of Denoising when Learning to Compress Images

Brummer, Benoit;De Vleeschouwer, Christophe
(2023) Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) — Location: Waikoloa, HI, USA (3.January.2023)

Files

Brummer_On_the_Importance_of_Denoising_When_Learning_To_Compress_Images_WACV_2023_paper.pdf
  • Open Access
  • Adobe PDF
  • 9.59 MB
Download

Details

Authors
Abstract
Image noise is ubiquitous in photography. However, image noise is not compressible nor desirable, thus attempting to convey the noise in compressed image bitstreams yields sub-par results in both rate and distortion. We propose to explicitly learn the image denoising task when training a codec. Therefore, we leverage the Natural Image Noise Dataset, which offers a wide variety of scenes captured with various ISO numbers, leading to different noise levels, including insignificant ones. Given this training set, we supervise the codec with noisy-clean image pairs, and show that a single model trained based on a mixture of images with variable noise levels appears to yield best-in-class results with both noisy and clean images, achieving better rate-distortion than a compression-only model or even than a pair of denoising-then-compression models with almost one order of magnitude fewer GMac operations.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Brummer, B., & De Vleeschouwer, C. (2023). On the Importance of Denoising when Learning to Compress Images. Proceedings of WACV 2023, 1(1), 2440-2448. https://hdl.handle.net/2078.5/105912 (Original work published 2023)