Noise-to-Compression Variational Autoencoder for Efficient End-to-End Optimized Image Coding

Symmetric image compression network with improved normalization attention mechanism

“…The Flicker2W 24 , 25 dataset is a highly regarded dataset that has gained significant recognition within the fields of computer vision and NLP. The Flicker2W dataset, with its diverse collection of images and accompanying captions, is not specifically designed for image compression tasks.…”

RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression

“…Within each GOP, the first frame, called I frame, is coded independently using image compression. A DNN-based image compression algorithm [41] is used to efficiently encode the I frame so that the P and B frames can refer to it with high quality. The P and B frames, which occupy most of the GOP, are constructed using video compression to remove temporal redundancy.…”

“…Furthermore, the R-D optimization adopted in DNN-based video compression enables higher compression efficiency by directly using the number of bits in the optimization procedure. To estimate the bit-rates, context models [7], [8], [41], [48], [65] are learned for the adaptive arithmetic coding method which compress discrete-valued data to bit-rates closely approaching the entropy of the representation. More recently, Yang et al [74] shows that hierarchical GOP structure can make use of the advantageous information from high-quality frames by improving the temporal predictive coding.…”