-
[pdf]
[bibtex]@InProceedings{Brummer_2023_WACV, author = {Brummer, Benoit and De Vleeschouwer, Christophe}, title = {On the Importance of Denoising When Learning To Compress Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {2440-2448} }
On the Importance of Denoising When Learning To Compress Images
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 the codec. Therefore, we leverage the Natural Image Noise Dataset, which offers a wide variety of scenes captured with various noise levels. Given this training set, we 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.
Related Material