Optimizing Image Compression via Joint Learning with Denoising

Cheng, Ka Leong; Xie, Yueqi; Chen, Qifeng

doi:10.1007/978-3-031-19800-7_4

Cited by 10 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We name this method "Joint Guidance without SNR-aware". The model architecture is similar to DC (Cheng, Xie, and Chen 2022). More details of this method are given in the supplementary material.…”

Section: Discussionmentioning

confidence: 99%

“…There are some works studied for joint solutions have made progress including joint denoising and demosaicing (Ehret et al 2019;Gharbi et al 2016), joint image demosaicing, denoising and super-resolution (Xing and Egiazarian 2021), joint low-light enhancement and denois-ing (Lu and Jung 2022), and joint low-light enhancement and deblurring (Zhou, Li, and Loy 2022). Recently, some works (Cheng, Xie, and Chen 2022;Alves de Oliveira et al 2022;Ranjbar Alvar et al 2022) optimize image processing and image compression jointly. Cheng et al (Cheng, Xie, and Chen 2022) jointed image compression and denoising to resolve the bits misallocation problem.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, some works (Cheng, Xie, and Chen 2022;Alves de Oliveira et al 2022;Ranjbar Alvar et al 2022) optimize image processing and image compression jointly. Cheng et al (Cheng, Xie, and Chen 2022) jointed image compression and denoising to resolve the bits misallocation problem. Jeong et al (Jeong and Jung 2022) proposed the RAWtoBit network (RBN), which jointly optimizes camera image signal processing and image compression.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Make Lossy Compression Meaningful for Low-Light Images

Cai,

Chen,

Zhong

et al. 2024

AAAI

View full text Add to dashboard Cite

Low-light images frequently occur due to unavoidable environmental influences or technical limitations, such as insufficient lighting or limited exposure time. To achieve better visibility for visual perception, low-light image enhancement is usually adopted. Besides, lossy image compression is vital for meeting the requirements of storage and transmission in computer vision applications. To touch the above two practical demands, current solutions can be categorized into two sequential manners: ``Compress before Enhance (CbE)'' or ``Enhance before Compress (EbC)''. However, both of them are not suitable since: (1) Error accumulation in the individual models plagues sequential solutions. Especially, once low-light images are compressed by existing general lossy image compression approaches, useful information (e.g., texture details) would be lost resulting in a dramatic performance decrease in low-light image enhancement. (2) Due to the intermediate process, the sequential solution introduces an additional burden resulting in low efficiency. We propose a novel joint solution to simultaneously achieve a high compression rate and good enhancement performance for low-light images with much lower computational cost and fewer model parameters. We design an end-to-end trainable architecture, which includes the main enhancement branch and the signal-to-noise ratio (SNR) aware branch. Experimental results show that our proposed joint solution achieves a significant improvement over different combinations of existing state-of-the-art sequential ``Compress before Enhance'' or ``Enhance before Compress'' solutions for low-light images, which would make lossy low-light image compression more meaningful. The project is publicly available at: https://github.com/CaiShilv/Joint-IC-LL.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Make Lossy Compression Meaningful for Low-Light Images

Cai,

Chen,

Zhong

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…The joint processing will instead add these details when reconstructing the data, which will not impact the data rate. Such joint processing already applies to compression and denoising operations with combined results superior to sequential results [4,5,6].…”

Section: Introductionmentioning

confidence: 99%

Joint Compression and Demosaicking For Satellite Images

Bacchus

Fraïssé

Roumy

et al. 2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Image sensors used in real camera systems are equipped with colour filter arrays which sample the light rays in different spectral bands. Each colour channel can thus be obtained separately by considering the corresponding colour filter. While existing compression solutions mostly assume that the captured raw data has been demosaicked prior to compression, in this paper, we describe an end-to-end trainable neural network for joint compression and demosaicking of satellite images. We first introduce a training loss combining a perceptual loss with the classical mean square error, which is shown to better preserve the high-frequency details present in satellite images. We then present a multi-loss balancing strategy which significantly improves the performance of the proposed joint demosaicking-compression solution.

show abstract

LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression

Zhang,

2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Optimizing Image Compression via Joint Learning with Denoising

Cited by 10 publications

References 49 publications

Make Lossy Compression Meaningful for Low-Light Images

Make Lossy Compression Meaningful for Low-Light Images

Joint Compression and Demosaicking For Satellite Images

LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression

Contact Info

Product

Resources

About