INR-MDSQC: Implicit Neural Representation Multiple Description Scalar Quantization for robust image Coding

TL;DR

This paper introduces INR-MDSQC, a neural network-based multiple description coding scheme for images that enhances error resilience and visual quality without requiring model training, outperforming traditional methods.

Contribution

The paper proposes a novel implicit neural representation approach for multiple description coding that simplifies implementation and improves flexibility and visual quality.

Findings

Competitive with autoencoder-based MDC

Superior visual quality over HEVC-based MDC

Eliminates need for model training

Abstract

Multiple Description Coding (MDC) is an error-resilient source coding method designed for transmission over noisy channels. We present a novel MDC scheme employing a neural network based on implicit neural representation. This involves overfitting the neural representation for images. Each description is transmitted along with model parameters and its respective latent spaces. Our method has advantages over traditional MDC that utilizes auto-encoders, such as eliminating the need for model training and offering high flexibility in redundancy adjustment. Experiments demonstrate that our solution is competitive with autoencoder-based MDC and classic MDC based on HEVC, delivering superior visual quality.