ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding

He, Dailan; Yang, Ziming; Peng, Weikun; Ma, Rui; Qin, Hongwei; Wang, Yan

doi:10.48550/arxiv.2203.10886

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diagram of the adopted networks. The right part is ELIC [15]. We use the same architecture of ga, gs, ha and hs as the original paper.…”

Section: Lic With Context Modelmentioning

confidence: 99%

See 1 more Smart Citation

PO-ELIC: Perception-Oriented Efficient Learned Image Coding

He¹,

Yang²,

Hou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate reconstructions of LIC suffer from artifacts such as blurring, color drifting and texture missing. Moreover, those varied artifacts make image quality metrics correlate badly with human perceptual quality. In this paper, we propose PO-ELIC, i.e., Perception-Oriented Efficient Learned Image Coding. To be specific, we adapt ELIC, one of the state-of-the-art LIC models, with adversarial training techniques. We apply a mixture of losses including hinge-form adversarial loss, Charbonnier loss, and style loss, to finetune the model towards better perceptual quality. Experimental results demonstrate that our method achieves comparable perceptual quality with HiFiC with much lower bitrate.

show abstract

“…Diagram of the adopted networks. The right part is ELIC [15]. We use the same architecture of ga, gs, ha and hs as the original paper.…”

Section: Lic With Context Modelmentioning

confidence: 99%

“…Then channel-wise context model is proposed [25]. ELIC [15] adopts a spatial-channel context modelling.…”

Section: Lic With Context Modelmentioning

confidence: 99%

PO-ELIC: Perception-Oriented Efficient Learned Image Coding

He¹,

Yang²,

Hou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ballé et al [2017] and formulate lossy neural image compression as a variational inference problem, by interpreting the additive uniform noise (AUN) relaxed scalar quantization as a factorized uniform variational posterior. After that, the majority of sota lossy neural image compression methods adopt this formulation , Minnen and Singh, 2020, Cheng et al, 2020, Guo et al, 2021a, Gao et al, 2021, He et al, 2022. And Yang et al [2020], Guo et al…”

Section: Lossy Neural Image and Video Compressionmentioning

confidence: 99%

“…Following He et al [2022], we train all the models on the largest 8000 images of ImageNet [Deng et al, 2009], followed by a downsampling according to . And we use Kodak [Kodak, 1993] for evaluation.…”

Section: Experimental Settingsmentioning

confidence: 99%

Multi-Sample Training for Neural Image Compression

Xu¹,

Wang²,

He³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper considers the problem of lossy neural image compression (NIC). Current state-of-the-art (sota) methods adopt uniform posterior to approximate quantization noise, and single-sample pathwise estimator to approximate the gradient of evidence lower bound (ELBO). In this paper, we propose to train NIC with multiple-sample importance weighted autoencoder (IWAE) target, which is tighter than ELBO and converges to log likelihood as sample size increases. First, we identify that the uniform posterior of NIC has special properties, which affect the variance and bias of pathwise and score function estimators of the IWAE target. Moreover, we provide insights on a commonly adopted trick in NIC from gradient variance perspective. Based on those analysis, we further propose multiple-sample NIC (MS-NIC), an enhanced IWAE target for NIC. Experimental results demonstrate that it improves sota NIC methods. Our MS-NIC is plug-and-play, and can be easily extended to other neural compression tasks.

show abstract

ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding

Cited by 2 publications

References 0 publications

PO-ELIC: Perception-Oriented Efficient Learned Image Coding

PO-ELIC: Perception-Oriented Efficient Learned Image Coding

Multi-Sample Training for Neural Image Compression

Contact Info

Product

Resources

About