Recently, numerous end-to-end optimized image compression neural networks have been
developed and proved themselves as leaders in rate-distortion performance. The main …

Learning-based image coding has attracted increasing attentions for its higher compression
efficiency than reigning image codecs. However, most existing learning-based codecs do …

Recently, DNN models for lossless image coding have surpassed their traditional
counterparts in compression performance, reducing the bit rate by about ten percent for …

Nonlinear transformations (NTs) are a crucial element of learned image compression (LIC)
as they eliminate correlations from images. However, there has been limited focus on …

The effective receptive field (ERF) plays an important role in transform coding, which
determines how much redundancy can be removed during transform and how many spatial …

Rate-distortion optimization through neural networks has accomplished competitive results
in compression efficiency and image quality. This learning-based approach seeks to …

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural
image compression methods, instead of more powerful vector quantization, due to the high …

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 …

Learned image compression (LIC) methods often employ symmetrical encoder and decoder
architectures, evitably increasing decoding time. However, practical scenarios demand an …

Recent video compression studies aim to compress videos in a more optimal space using
deep neural networks. Most of them employ a strategy where they use motion information to …