Controlling rate, distortion, and realism: Towards a single comprehensive neural image compression model

S Iwai, T Miyazaki, S Omachi - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
In recent years, neural network-driven image compression (NIC) has gained significant
attention. Some works adopt deep generative models such as GANs and diffusion models to …

Yoda: You only diffuse areas. an area-masked diffusion approach for image super-resolution

BB Moser, S Frolov, F Raue, S Palacio… - arxiv preprint arxiv …, 2023 - arxiv.org
This work introduces" You Only Diffuse Areas"(YODA), a novel method for partial diffusion in
Single-Image Super-Resolution (SISR). The core idea is to utilize diffusion selectively on …

Balance of number of embedding and their dimensions in vector quantization

H Chen, SS Reddy, Z Chen, D Liu - arxiv preprint arxiv:2407.04939, 2024 - arxiv.org
The dimensionality of the embedding and the number of available embeddings (also called
codebook size) are critical factors influencing the performance of Vector Quantization (VQ), a …

Learning-Based Image Compression With Parameter-Adaptive Rate-Constrained Loss

ND Guerin, RC da Silva… - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
In recent years, the crucial task of image compression has been addressed by end-to-end
neural network methods. However, achieving fine-grained rate control in this new paradigm …

VRVQ: Variable Bitrate Residual Vector Quantization for Audio Compression

Y Chae, W Choi, Y Takida, J Koo, Y Ikemiya… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent state-of-the-art neural audio compression models have progressively adopted
residual vector quantization (RVQ). Despite this success, these models employ a fixed …