Controlling rate, distortion, and realism: Towards a single comprehensive neural image compression model
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 …
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
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 …
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
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 …
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 …
neural network methods. However, achieving fine-grained rate control in this new paradigm …
VRVQ: Variable Bitrate Residual Vector Quantization for Audio Compression
Recent state-of-the-art neural audio compression models have progressively adopted
residual vector quantization (RVQ). Despite this success, these models employ a fixed …
residual vector quantization (RVQ). Despite this success, these models employ a fixed …