Towards the Perceptual Quality Enhancement of Low Bit-rate Compressed Images

Kim, Younhee; Cho, Seung-Hyun; Lee, Jooyoung; Jeong, Se Yoon; Choi, Jin Soo; Do, Jihoon

doi:10.1109/cvprw50498.2020.00076

Cited by 12 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of output channels of the side encoder and decoder are set to 32 and three, respectively. The post filter is based on a lightweight version of HGRDN [17]. BPG and VVC with chroma format 420 are used for the conventional compression.…”

Section: Experimental Settingsmentioning

confidence: 99%

Quality Enhancement of Conventional Compression with a Learned Side Bitstream

NARUKO,

AKUTSU,

TSUBOTA

et al. 2023

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

We propose Quality Enhancement via a Side bitstream Network (QESN) technique for lossy image compression. The proposed QESN utilizes the network architecture of deep image compression to produce a bitstream for enhancing the quality of conventional compression. We also present a loss function that directly optimizes the Bjontegaard delta bit rate (BD-BR) by using a differentiable model of a rate-distortion curve. Experimental results show that QESN improves the rate by 16.7% in the BD-BR compared to Better Portable Graphics.

show abstract

Section: Experimental Settingsmentioning

confidence: 99%

Quality Enhancement of Conventional Compression with a Learned Side Bitstream

NARUKO,

AKUTSU,

TSUBOTA

et al. 2023

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Most such works paired the standard codec with either a neural pre-processor alone (e.g., to perform denoising of the input image [19]- [21]) or a neural post-processor alone (e.g., to perform deblocking or other enhancements of the output image [22]- [24]). A few works paired standard codecs with both neural pre-and post-processors, such as [25]- [29], but these solutions, like prior non-neural solutions such as [30] or the "frame super-resolution" mode of VP9, did so in such a way that the pre-and post-processors may be used independently; thus no neural codes are generated; hence they do not take full advantage of the communication available between the pre-and post-processors (see Proposition 1).…”

Section: Introductionmentioning

confidence: 99%

Sandwiched Image Compression: Increasing the resolution and dynamic range of standard codecs

Guleryuz

Chou

Hoppe

et al. 2022

2022 Picture Coding Symposium (PCS)

View full text Add to dashboard Cite

We propose sandwiching standard image and video codecs between pre-and post-processing neural networks. The networks are jointly trained through a differentiable codec proxy to minimize a given rate-distortion loss. This sandwich architecture not only improves the standard codec's performance on its intended content, it can effectively adapt the codec to other types of image/video content and to other distortion measures. Essentially, the sandwich learns to transmit "neural code images" that optimize overall rate-distortion performance even when the overall problem is well outside the scope of the codec's design. Through a variety of examples, we apply the sandwich architecture to sources with different numbers of channels, higher resolution, higher dynamic range, and perceptual distortion measures. The results demonstrate substantial improvements (up to 9 dB gains or up to 30% bitrate reductions) compared to alternative adaptations. We derive VQ equivalents for the sandwich, establish optimality properties, and design differentiable codec proxies approximating current standard codecs. We further analyze model complexity, visual quality under perceptual metrics, as well as sandwich configurations that offer interesting potentials in image/video compression and streaming.

show abstract

“…Neural preprocessing addresses denoising [4,5,6], and neural postprocessing is commonly used to reduce blocking and other coding artifacts [7,8,9]. In particular, Kim et al [10] improve the output of the VVC/H266 intraframe codec using residual dense networks (RDNs) and generative adversarial networks (GANs) to win the CVPR 2020 Learned Image Compression Challenge. In contrast our contribution is to consider a neural sandwich where the standard codec operates on images in a new space, i.e., a latent space optimized for a particular class of input data.…”

Section: Introductionmentioning

confidence: 99%

Sandwiched Image Compression: Wrapping Neural Networks Around A Standard Codec

Guleryuz

Chou

Hoppe

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

We sandwich a standard image codec between two neural networks: a preprocessor that outputs neural codes, and a postprocessor that reconstructs the image. The neural codes are compressed as ordinary images by the standard codec. Using differentiable proxies for both rate and distortion, we develop a rate-distortion optimization framework that trains the networks to generate neural codes that are efficiently compressible as images. This architecture not only improves ratedistortion performance for ordinary RGB images, but also enables efficient compression of alternative image types (such as normal maps of computer graphics) using standard image codecs. Results demonstrate the effectiveness and flexibility of neural processing in mapping a variety of input data modalities to the rigid structure of standard codecs. A surprising result is that the rate-distortion-optimized neural processing seamlessly learns to transport color images using a single-channel (grayscale) codec.

show abstract

Towards the Perceptual Quality Enhancement of Low Bit-rate Compressed Images

Cited by 12 publications

References 6 publications

Quality Enhancement of Conventional Compression with a Learned Side Bitstream

Quality Enhancement of Conventional Compression with a Learned Side Bitstream

Sandwiched Image Compression: Increasing the resolution and dynamic range of standard codecs

Sandwiched Image Compression: Wrapping Neural Networks Around A Standard Codec

Contact Info

Product

Resources

About