Neural Data-Dependent Transform for Learned Image Compression

03/09/2022
by   Dezhao Wang, et al.
0

Learned image compression has achieved great success due to its excellent modeling capacity, but seldom further considers the Rate-Distortion Optimization (RDO) of each input image. To explore this potential in the learned codec, we make the first attempt to build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding efficiency for each individual image. Specifically, apart from the image content stream, we employ an additional model stream to generate the transform parameters at the decoder side. The presence of a model stream enables our model to learn more abstract neural-syntax, which helps cluster the latent representations of images more compactly. Beyond the transform stage, we also adopt neural-syntax based post-processing for the scenarios that require higher quality reconstructions regardless of extra decoding overhead. Moreover, the involvement of the model stream further makes it possible to optimize both the representation and the decoder in an online way, i.e. RDO at the testing time. It is equivalent to a continuous online mode decision, like coding modes in the traditional codecs, to improve the coding efficiency based on the individual input image. The experimental results show the effectiveness of the proposed neural-syntax design and the continuous online mode decision mechanism, demonstrating the superiority of our method in coding efficiency compared to the latest conventional standard Versatile Video Coding (VVC) and other state-of-the-art learning-based methods.

READ FULL TEXT
research
07/06/2020

ModeNet: Mode Selection Network For Learned Video Coding

In this paper, a mode selection network (ModeNet) is proposed to enhance...
research
07/12/2023

ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression

Over the last few years, neural image compression has gained wide attent...
research
07/12/2023

AICT: An Adaptive Image Compression Transformer

Motivated by the efficiency investigation of the Tranformer-based transf...
research
07/05/2023

Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compression

Recently, the performance of neural image compression (NIC) has steadily...
research
06/21/2022

Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Map, and Post-Quantization Filtering

Recently, deep learning-based image compression has made signifcant prog...
research
05/03/2023

Toward Textual Transform Coding

Inspired by recent work on compression with and for young humans, the su...
research
06/21/2023

Recoil: Parallel rANS Decoding with Decoder-Adaptive Scalability

Entropy coding is essential to data compression, image and video coding,...

Please sign up or login with your details

Forgot password? Click here to reset